Open AccessReview

Interdisciplinary Perspectives on Agent-Based Modeling in the Architecture, Engineering, and Construction Industry: A Comprehensive Review

Silvia Mazzetto

Sustainable Architecture Laboratory, College of Architecture and Design, Department of Architecture, Prince Sultan University, Riyadh 12435, Saudi Arabia

Buildings 2024, 14(11), 3480; https://doi.org/10.3390/buildings14113480

Submission received: 17 September 2024 / Revised: 28 October 2024 / Accepted: 29 October 2024 / Published: 31 October 2024

(This article belongs to the Section Construction Management, and Computers & Digitization)

Download

Browse Figures

Versions Notes

Abstract

This paper explores the transformative impact of agent-based modeling (ABM) on the architecture, engineering, and construction (AEC) industry, highlighting its indispensable role in revolutionizing project management, construction processes, safety protocols, and sustainability initiatives including energy optimization and occupants’ comfort. Through an in-depth review of 178 documents published between 1970 and 2024 on current practices and the integration of ABM with emerging digital technologies, this study underscores the critical importance of ABM in facilitating enhanced decision-making, resource optimization, and complex system simulations. For instance, ABM is shown to reduce project delays by up to 15% through enhanced resource allocation and improve safety outcomes by simulating worker behavior and identifying potential hazards in dynamic construction environments. The results reveal ABM’s potential to significantly improve construction methodologies, integrate technological advancements seamlessly, and contribute to the development of sustainable and resilient building practices. Furthermore, this paper identifies key areas for future research, including the exploration of ABM’s capabilities in conjunction with other digital innovations to unlock new avenues for efficiency and sustainability in construction. This study sets out a forward-looking agenda for providing this modeling approach to address contemporary challenges and harness opportunities for innovation and growth in the AEC sector.

Keywords:

agent-based modeling; project management; construction management; safety; sustainability; digital technologies; resource optimization; complex systems; sustainable building practices; resilience

1. Introduction

Agent-based modeling (ABM), also known by various names such as agent-based simulation (ABS), agent-based modeling and simulation (ABMS), multiagent simulation (MAS), and multiagent-based simulation (MABS), represents a significant leap forward in the domain of computational simulations, a tool that has become increasingly indispensable across nearly every scientific discipline [1]. This technique, benefiting from the exponential growth in computing power, enables the detailed simulation of complex systems by modeling the interactions among autonomous agents within a specified environment [2]. Each agent in an ABM system is programmed with distinct behaviors and decision-making capabilities, allowing for the study of emergent phenomena that arise from the collective interactions of these individual entities [3]. This approach to modeling, which looks at the micro-level actions and their impact on the macro system, has been facilitated by the advent of simulation techniques that not only save considerable time, cost, and effort, but also enhance accuracy and predictive power [4]. ABM’s ability to mimic real-world systems more closely has cemented its role as a powerful simulation modeling technique [5]. Its application spans across various fields, providing its unique characteristics to model distinctive agents, parameters, and traits, thereby offering profound insights into the dynamics of complex systems without the need to directly intervene in real-world systems [6]. This paper aims to explore the nuances of ABM, highlighting its distinguishing features, particularly in the AEC domain, and outlining the objectives and scope of this review, thereby setting the stage for a comprehensive exploration of this versatile modeling tool’s potential.

1.1. ABM Background

The foundational concept of ABM has its roots in the early 20th century [7]. During the 1930s, Enrico Fermi tackled the complex problem of neutron diffusion in substances [8]. He encountered the challenge that neutrons’ paths were probabilistic, with many possible interactions at each step. Traditional methods failed to predict their collective behavior due to the complexity. Fermi solved this by simulating individual neutron pathways using a mechanical calculator, (Marchant Calculating Machine Company, located in Oakland, CA, USA) an early example of agent-based modeling (ABM) [9,10,11,12].

The versatility of ABM has led to its application in a diverse array of fields, ranging from social sciences to economics, environmental studies, geography, and socio-technical systems [13]. Macal and North have extensively categorized these applications, broadly dividing them into computing and non-computing scientific domains [14].

The conceptual map provided in Figure 1 outlines the various facets and applications of ABM, categorizing them into interconnected domains, thus highlighting its core concepts, interactions, applications, techniques, and analyses. At the center is “agent-based modeling”, branching out to key concepts like “agents”, “environment”, and “interactions”, which detail agent properties, behaviors, and the spatial and temporal dynamics they navigate. Applications extend into various fields, demonstrating ABM’s versatility, from social sciences and market dynamics to engineering and epidemiology. Techniques and analysis tools such as simulation, sensitivity analysis, and parameter tuning are also depicted, showcasing the methodological approaches used to study both continuous processes and discrete events within ABM.

ABM has undergone a significant transformation since its inception in the 1970s through to 2024, expanding across a spectrum of disciplines and incorporating increasingly complex computational techniques [19,20]. This evolution can be delineated into three distinct phases, each marked by novel applications and methodological advancements [21].

The early phase, spanning from 1970 to 1999, was characterized by ABM’s application to ecological and biological systems [22,23,24].

The period from 2000 to 2010 witnessed a paradigm shift, with ABM extending into the realm of various disciplines and sciences [25,26,27,28]. This period also saw the growth of multi-agent systems (MAS) in computing and engineering, blurring the lines between these disciplines and ABM [29].

From 2010 to 2024, ABM’s prevalence in social science [30], epidemiology [31], economics [32], and industrial business research [33] became more pronounced, with applications in many fields [34,35,36,37]. The integration of machine learning algorithms with ABM led to more sophisticated agent behaviors and enhanced model calibration, signaling a new era of intelligent system simulations [38,39,40,41].

Figure 2 and Table 1 visualize the topics of papers related to ABM published from 1970 to 2024. Initially, papers were mostly concentrated in the fields of Economics and Social Science, which could indicate the early adoption of ABM in these areas to model complex systems and behaviors. As the years progressed, a significant increase in the number of papers can be seen, especially from the 1990s onwards, reflecting ABM’s growing popularity and applications. Notably, Computer Science, Building Economy, and Land Use, and Engineering topics show an uptick in ABM-related papers, suggesting the broadening of ABM’s applicability in simulating and analyzing systems within these fields.

1.2. Subsection ABM in Architecture, Engineering and Construction (AEC)

ABM emerges as an important approach in computational simulations, transcending traditional methods like discrete-event simulation (DES) and system dynamics (SD) by embracing the complexity and heterogeneity inherent in real-world systems [50]. ABM differs from system dynamics (SD) and discrete event simulation (DES) by focusing on the interactions between individual agents, each with distinct behaviors, while SD models aggregate system-level variables, and DES focuses on processes where events occur at discrete points in time. Unlike the top-down approach of SD or the process-oriented DES, ABM uses a bottom-up approach to capture the complexity of agent interactions. ABM’s primary advantage over SD and DES in the AEC industry lies in its ability to model heterogeneous agents and their interactions, offering more detailed insights into how individual behaviors and decisions impact overall project outcomes. This flexibility allows ABM to address complex scenarios such as construction worker coordination, building performance, and resource allocation in ways that SD and DES cannot. Despite its strengths, ABM has limitations, including the increased computational demand required for simulating large systems and the challenge of calibrating agent behaviors accurately. Additionally, ABM models can become overly complex, making them harder to validate and interpret compared to simpler SD or DES models. ABM is chosen over SD or DES when the goal is to study complex interactions among diverse entities with varying behaviors, such as in construction site management or occupant behavior in smart buildings. ABM’s ability to simulate emergent behaviors from individual-level interactions provides a level of detail and realism that is often essential for addressing the intricacies of AEC projects. Unlike these conventional techniques, which often assume homogeneity among agents and a top-down analysis framework, ABM distinguishes itself through its capacity to model agents with diverse characteristics within the same group, thereby offering a more precise representation of individual behaviors [51] and their cumulative impact on system dynamics [52]. This granular approach not only enhances the realism and accuracy of simulations but also broadens the scope for exploring multifaceted problems [53] through the generation of varied scenarios, thereby increasing the likelihood of identifying efficient solutions amidst complex options [6].

The diversity of agent characteristics and interactions in agent-based modeling (ABM) significantly enhances the accuracy and predictive power in the architecture, engineering, and construction (AEC) sectors. This diversity allows for the simulation of a wide range of behaviors and decision-making processes among various stakeholders, such as contractors, suppliers, and clients. By incorporating distinct attributes, preferences, and interactions, ABM can capture the complexities and dynamics of real-world scenarios more effectively. As a result, models become better equipped to reflect the nuances of human behavior and the intricate relationships within the construction ecosystem, ultimately leading to more reliable predictions and informed decision-making.

ABM’s flexibility in handling time progression—be it discrete, continuous, or a hybrid—further allows for the dynamic updating of agent interactions and behaviors, setting the stage for simulations that closely mirror the intricacies of real-world conditions [54].

In architecture and construction management, the application of ABM addresses the multifaceted challenges of designing, fabricating, and managing buildings, capturing the complex interactions between occupants and the built environment [55]. Traditional architectural modeling, while adept at conveying form and function through iconic, analog, and symbolic models, often falls short in grappling with the complexities and emergent properties characteristic of architectural systems [56]. ABM, by contrast, serves as a generative model capable of simulating complex systems through detailed interaction topologies between agents, thereby fostering a deeper understanding of phenomena such as complexity, emergence, and self-organization within architectural contexts [55]. This simulation-based approach not only facilitates the exploration of novel design possibilities in the early stages of architectural design but also supports the convergence towards optimal solutions through techniques like particle swarm optimization (PSO), effectively marrying the exploratory and goal-oriented facets of architectural space planning [57]. Thus, ABM stands as a pivotal tool in advancing the field of architectural design, engineering, and construction, offering unparalleled insights into the dynamic interplay of elements that define and influence the built environment [58].

Building upon this foundation, it is critical to differentiate between the individual “agents” and the broader concept of “agent-based modeling” (ABM). An agent is defined as an autonomous entity with decision-making capabilities, tailored to act or react based on its objectives, rules, and interactions within a simulated environment [59]. These agents, embodying distinct traits and behaviors, serve as the dynamic constituents of an ABM system [60]. Conversely, ABM represents the comprehensive framework that orchestrates the collective behavior of these agents, aiming to replicate and understand the emergent dynamics of the complex systems they form [61]. Through this distinction, we grasp that while agents are the micro-level actors within simulations [62], ABM provides the macro-level perspective, analyzing how interactions among multiple agents give rise to the system’s overall behavior, thereby bridging individual actions with collective outcomes [20]. This layered understanding enhances our ability to simulate, analyze, and derive solutions for complex architectural and construction challenges, marking a significant evolution in the field’s approach to design and management [63].

Recent publications illustrate a notable trend towards integrating agent-based modeling (ABM) with real-time data analytics and digital twins [64,65,66], significantly enhancing the capabilities of modeling complex systems in architecture, engineering, and construction [67,68,69,70,71,72]. Studies such as those on developing human-centered urban digital twins emphasize the necessity for multi-agent interactions and artificial intelligence, aligning perfectly with ABM principles to bolster community resilience [73,74,75,76,77,78,79,80]. Furthermore, the analysis of digital twin research trends reveals a growing reliance on real-time data and sensor technologies, which are pivotal for effective ABM applications. In the context of smart manufacturing and urban management, several papers highlight frameworks where ABM synergizes with digital twins to facilitate real-time monitoring and decision-making, thereby improving operational efficiency and adaptability. This convergence of methodologies provides a contemporary perspective on the topic, demonstrating how integrating these technologies addresses existing gaps and enhances the practical application of ABM in real-world scenarios. Collectively, these advancements signify an evolution in research, positioning ABM as a critical tool in the digital transformation of various sectors, particularly in enhancing infrastructure resilience and optimizing resource management.

Agent-based modeling (ABM) has had significant patent achievements in architecture, engineering, and the construction industry, reflecting its growing interdisciplinary impact. Patents in this field focus on innovations like using agent-based frameworks for optimizing material selection, robotic fabrication processes, and adaptive building designs. These patents support advancements in computational design, facilitating complex tasks such as the coordination of mobile robotic systems for construction and the development of smart, sustainable buildings. For example, interactive ABM frameworks have been applied to improve the efficiency and precision of architectural designs, especially in adaptive and sustainable projects [81,82]. These innovations illustrate the importance of ABM in creating smarter, more responsive environments that align with sustainability goals, offering practical applications in both traditional and futuristic construction methodologies. These developments enhance not only technical efficiencies but also contribute to long-term sustainability and smart city initiatives [83].

1.3. Scope of the Study

Within the sphere of AEC, where the complexity and dynamic nature of challenges are ever-present due to the myriad of fluctuating factors, ABM stands out as a strategic approach to dissect and understand these multifaceted issues. The ability of ABM to forecast diverse scenario outcomes and pinpoint the most viable solutions underscores its burgeoning use in AEC research. Despite a noticeable uptick in ABM-centric studies in the recent past, there remains a notable dearth of comprehensive review literature that encapsulates these developments. Our endeavor through this research is to mend this gap by providing an exhaustive review of the breadth of ABM applications throughout the AEC industry. Compared to [84], this effort will employ a combined methodological framework, providing both bibliometric and qualitative content analysis, to chart the progression and present landscape of ABM within the construction sphere. This initiative is poised to transcend previous literature limitations, such as linguistic constraints and incomplete literature scopes, by broadening the investigative lens to encompass an extensive range of publications and adopting more encompassing categorizations reflective of ABM’s diverse utility in construction.

Additionally, compared to [1,55], this study is tailored to tackle the identified gaps and anticipated future research avenues within ABM’s application in AEC. The utilization of ABM in AEC remains partially untapped, with significant potential lying in less explored areas. For example, areas critical to the construction industry’s operational efficacy, such as energy efficiency and the well-being of occupants, offer rich ground for future ABM explorations, beyond the traditionally emphasized safety-centric studies. Our investigation also extends to ABM’s role in emerging technologies and methodologies, including the fine-tuning of 3D printing in construction [85] and the enhancement of sustainable building operations [86,87,88,89].

Moreover, the ambition of our research is to cultivate a more inclusive modeling paradigm that fully appreciates the spectrum of agent attributes and behaviors, particularly those affecting workforce dynamics and the integration of ABM with other simulation and technological tools like digital twin, BIM, and advanced sensing technologies. This comprehensive review aims to map the current trends and gaps within ABM applications in AEC and to forge a forward-looking perspective on how ABM can be provided to foster innovation in construction methodologies, including advocating for open source collaborative platforms, exploring hybrid simulation models, and enhancing model validation through empirical studies.

The inclusion of organizational readiness in the context of ABM and BIM is crucial for the effective implementation of these methodologies in AEC. Insights from recent studies [90,91] reveal that the successful integration of ABM and BIM is contingent upon assessing an organization’s readiness and capabilities. Understanding the underlying factors that enable or hinder BIM adoption will enhance the discussion around ABM’s application and its alignment with organizational goals. This focus on organizational readiness will not only complement our exploration of ABM’s potential but also provide a holistic view of its impact on improving efficiency and sustainability in construction practices.

The scope of this paper extends the current discourse by incorporating a comprehensive survey of industry experts, thereby unveiling novel insights into ABM’s practical effectiveness and application challenges. Unlike previous studies that predominantly focused on theoretical frameworks or limited case studies, our research bridges the gap between theoretical potential and real-world applications through the lens of experienced professionals.

This research endeavors to enrich the knowledge base, guiding both practitioners and scholars towards novel, efficient, and sustainable construction methodologies by venturing beyond the limitations identified in previous reviews and explore the depths of ABM’s potential across all construction phases. Through this thorough investigation, this study will illuminate the pathways for future research and development in ABM applications, contributing significantly to the evolution of construction practices.

2. Methods

Our study’s methodological framework, outlined in Figure 3, was a structured five-step process that underpinned the systematic collection and analysis of literature pertaining to ABM in the AEC field between 1970 and 2024. The first step involved the development of a set of search terms tailored to capture the pertinent intersection of ABM and construction. The second step was the execution of a comprehensive literature search across multiple databases, including Web of Science, Scopus, and Google Scholar, ensuring a broad collection of potential articles.

Following the search, the third step was to filter the initial results, which involved the critical exclusion of irrelevant papers, leading to a refined selection of studies that were the focus of further analysis. The fourth step was the in-depth analysis of the chosen literature, where data were extracted, preprocessed, and then examined using Python 3.12 for a more rigorous and computational approach to understanding the existing research landscape.

The final and fifth step was dedicated to synthesizing the findings from the literature analysis. This involved summarizing the key outcomes, identifying existing research gaps, and considering the implications for future research directions. This synthesis aimed to build a cohesive understanding of the state of ABM research in construction and to guide subsequent scholarly inquiry in this burgeoning area.

For the initial stage of literature collection in our study, the “Scopus” and “Web of Science” databases were utilized as the primary sources for the scientific literature, supplemented by additional searches in “Google Scholar”, as well as targeted journals’ websites, to ensure comprehensive coverage. To align the search results with the focus on both ABM and the AEC industry, two distinct sets of keywords were formulated. Searches were conducted using every possible pairing of these keywords, linked by the conjunction “AND”. This strategy was employed within publication dates ranging from 1990 to 2024 to capture contemporary developments in the field.

The pursuit of the relevant literature was characterized by an inclusive retrieval approach, moving beyond the constraints of author-specified keywords to encompass titles, abstracts, and keywords in the initial phase and expanding to all document fields in subsequent searches. Such breadth in the search criteria was designed to ensure the maximum inclusion of pertinent papers while acknowledging that it would result in a higher volume of initial results, which was subsequently addressed through meticulous manual screening.

The screening process entailed the removal of duplicates and off-topic documents. However, this research included non-English language materials and gray literature such as conference proceedings, books, dissertations, theses, and reports in order to perform as comprehensive a review as possible.

To address the inclusion of non-peer-reviewed literature in our review, we implemented a carefully structured selection and validation process to mitigate any potential impact on the rigor of our findings. Non-peer-reviewed sources, such as conference proceedings and gray literature, were included only when they offered unique or emerging insights not readily available in peer-reviewed journal articles. We conducted a preliminary assessment to identify whether these sources provided substantial value to our analysis, excluding any that duplicated or overlapped with existing journal findings. Additionally, we prioritized non-peer-reviewed documents that were authored by recognized experts or affiliated with reputable institutions to further enhance credibility. By implementing this selective and evaluative approach, we ensured that non-peer-reviewed literature served as a complementary resource, adding depth and a broader perspective to this study without compromising the integrity of our review.

Preliminary assessments indicated that non-journal documents, particularly conference papers which often precede or replicate journal articles, did not contribute additional insights beyond those found in the journals. The final curation process involved a detailed review of the filtered articles to affirm their relevance, culminating in a curated collection of 178 journal papers deemed suitable for review.

The selection criteria for papers in this study emphasized peer-reviewed journal articles as the primary data source due to their rigorous review processes, which ensure a higher standard of validity and reliability in the findings. Including only peer-reviewed literature allowed us to build on work that has undergone scrutiny by experts in the field, reducing potential biases and increasing the robustness of our analysis. The exclusion of non-peer-reviewed sources, such as conference proceedings and gray literature, was a deliberate choice aimed at maintaining the methodological rigor of our study. While conference papers and gray literature can provide valuable, emerging insights, their inclusion without strict vetting may introduce unverified data and compromise the validity of our conclusions. By focusing on peer-reviewed articles, the aim was to provide a well-founded synthesis that can reliably inform future research and practice in the ABM and AEC fields. The search strategy was carefully constructed using a combination of key terms related to ABM and the AEC industry, interconnected with Boolean operators to ensure a broad yet precise capture of relevant literature. The keywords included “Agent-based Modeling”, “AEC”, “Architecture, Engineering, and Construction”, “construction project management”, “sustainable building design”, “Digital twin”, “BIM integration”, “construction safety”, “workforce dynamics”, “3D printing in construction”, “collaborative platforms for ABM”, “hybrid simulation models”, and “advanced sensing technologies”. These terms were linked using the Boolean operators “AND” to narrow the search to documents that include essential concepts together and “OR” to expand the search to encompass a variety of related subjects.

To ensure a thorough and unbiased review of the articles selected for this study, we adopted a tripartite analysis strategy that seamlessly integrated quantitative and qualitative methods. This integrated approach was crucial for mitigating biases and subjective interpretations often associated with purely qualitative reviews, thus fostering a more balanced and comprehensive understanding of the subject matter. This methodology aligned with prior research suggestions that highlight the importance of combining analytical methods to achieve a deeper and more accurate perception of a given topic [92]. Initially, our analysis commenced with a bibliometric examination of the 178 articles that met our selection criteria. This quantitative phase allowed us to assess various dimensions of literature, including publication frequencies, countries, and trends in keyword usage.

Subsequently, we performed a qualitative review of the article contents, systematically categorizing the literature based on the specific phases of construction addressed and the distinct applications of ABM within these contexts. This stage facilitated the identification of dominant trends and the summarization of pertinent findings across various categories, thereby providing a detailed snapshot of the field’s current landscape. The culmination of this methodological approach involved synthesizing insights from both the bibliometric and qualitative analyses. This synthesis aimed to conduct an in-depth examination of the categorized areas, exploring the dispersion of publications and their chronological development. In this way, we were able to pinpoint areas with extensive research activity as well as emerging trends marked by rapid growth in recent publications. This dual-faceted analysis thereby served to map the application landscape of ABM in the AEC industry comprehensively, underscoring influential domains and forecasting promising directions for future inquiry.

In the review and analysis of the selected documents for this study, a methodological approach was incorporated by utilizing JSON data formats [93] and Python programming [94] to analyze the data extracted from the literature. This digital approach enabled us to efficiently manage and process the vast amount of information derived from the 178 documents that constituted our primary dataset.

The integration of Python and JSON not only enhanced the accuracy and efficiency of our quantitative analysis but also supported a more nuanced qualitative review. Through custom scripts and algorithms, we reproduced data from various sources, synthesizing existing knowledge with newly identified insights. This process was pivotal in systematically categorizing the literature into distinct groups based on construction phases and ABM applications, enabling the identification of prevailing trends and the summarization of significant findings. This innovative analytical approach allowed us to not only map the current landscape of ABM applications in the AEC industry comprehensively but also to generate new knowledge by uncovering patterns and connections that inform future research directions.

In addition, and as part of our comprehensive study on the effectiveness of ABM within the AEC industry, we devised a detailed survey aimed at capturing expert opinions across various facets of ABM application. This survey consisted of a series of questions designed to assess the perceived effectiveness of ABM in areas such as Workflow Optimization, Resource Allocation, Project Timeline Management, Safety and Risk Management, Collaboration Efficiency, Design Changes, Environmental Impact, and Financial Implications. Each question was structured on a Likert scale from 1 (Not Effective) to 5 (Very Effective), allowing for nuanced responses that reflected the experts’ assessments of ABM’s impact in their respective fields.

To ensure a broad and informed perspective, we targeted a diverse group of professionals within the AEC industry, including architects, engineers, construction managers, project managers, and sustainability consultants, among others. These individuals were identified and contacted through professional networks, industry associations, and academic partnerships, leveraging both direct outreach via email and indirect solicitation through industry forums and social media platforms. Experts were selected based on their demonstrated experience and contributions to the field, with a particular focus on those who have directly engaged with or studied the implications of ABM in their work.

Upon agreeing to participate, experts were provided with access to the online survey platform, which was designed for ease of use and confidentiality. The survey period was open for two weeks, allowing sufficient time for participants to respond at their convenience. To encourage participation and ensure a high response rate, reminders were sent out bi-weekly, highlighting the importance of their expert insights to advancing the understanding of ABM in the AEC industry. Participation was voluntary, with an emphasis on the anonymous and aggregate presentation of the data to preserve confidentiality and encourage candid responses.

Following the closure of the survey period, responses (from 36 experts) were compiled and analyzed to derive average effectiveness ratings for each area of ABM application.

3. Results

In this section, we explore the findings of our comprehensive review of ABM applications across the AEC industry. Our investigation, propelled by the ambition to bridge the gap identified in the previous literature, employs a combined methodological framework that encompasses both bibliometric and qualitative content analyses. This dual approach enables us to chart the progression, delineate the current landscape, and unveil the burgeoning potential of ABM within the construction sphere with unprecedented clarity and depth. While ABM’s theoretical framework provides valuable insights into system behaviors, its practical applications in architecture, particularly in advancing sustainability, cannot be overlooked. ABM has been increasingly applied in architectural design to optimize energy performance, improve occupant well-being, and promote the sustainable use of resources. Real-world examples include the simulation of energy-efficient designs, where ABM models are used to predict and adjust energy consumption based on occupant behaviors. Furthermore, ABM has been instrumental in developing adaptive building systems that respond to environmental conditions and user needs in real-time, enhancing the sustainability of urban planning projects. By integrating ABM with digital twins and building management systems, architects can continuously optimize building operations, ensuring long-term energy efficiency and sustainability. This practical integration illustrates how ABM serves as a transformative tool in addressing the environmental challenges of contemporary architecture, moving beyond theoretical models to tangible, sustainable solutions.

3.1. Bibliometric Analysis

In this section, the bibliographic analysis of the reviewed papers is shown in different dimensions based on the publication source, country, and topic.

Figure 4 represents the results of a survey conducted with experts from the AEC industry regarding the effectiveness of ABM in various aspects of the industry. Each bar reflects the average rating given by these experts on a scale from 1 to 5, with 5 denoting “very effective” and 1 denoting “not effective”. The results indicate strong confidence in ABM’s effectiveness across several key areas. Workflow Optimization, Resource Allocation, and Environmental Impact received particularly high ratings, suggesting that experts believe that ABM can significantly improve these areas. The slightly lower but still positive ratings for Project Timeline, Safety and Risk Management, and Collaboration highlight areas where ABM is seen as beneficial, though perhaps with room for further development or application. Design Changes and Financial Implications also scored well, indicating a broad consensus on ABM’s potential to positively influence a wide range of outcomes in the AEC industry.

Moreover, each cell in Figure 5 represents the correlation coefficient between two aspects, ranging from −1 (perfect negative correlation) to +1 (perfect positive correlation), with 0 indicating no correlation. High positive values suggest that experts who rate one aspect of ABM as effective tend to also rate other aspects as effective, indicating interconnected benefits of ABM applications. For instance, in the heatmap provided, the correlation between “Workflow Optimization” and “Design Changes” is notably high at 0.85, suggesting a strong positive relationship. This implies that experts who perceive ABM as highly effective in optimizing workflow processes also tend to recognize its significant impact on facilitating design changes. This could be due to ABM’s ability to simulate various scenarios, enabling better decision-making which not only streamlines workflow but also supports the adaptability and efficiency of design modifications in response to project needs or constraints. Similarly, the correlation of 0.95 between “Environmental Impact” and “Financial Implications” indicates that improvements in environmental sustainability through ABM application are closely associated with positive financial outcomes, perhaps through cost savings or enhanced project value. These can inform stakeholders in the AEC industry about the multifaceted benefits of ABM, encouraging its integrated application across project planning, execution, and evaluation phases. To further enhance the modeling of diverse agent behaviors in ABM applications, it is essential to address variability within agent populations. Also incorporating recent study methods [95] allows for a more nuanced representation of agent diversity, improving the accuracy of simulations. DSPS facilitates the systematic reproduction of different sub-populations by focusing on key characteristics and behaviors, enabling the model to reflect real-world variations more effectively. By employing this method, ABM can better capture the complexities inherent in the AEC industry, leading to more reliable predictions and insights that account for the variability in agent interactions and outcomes.

The depiction of publication trends over the last four decades, as illustrated in Figure 6, unveils patterns that illuminate the evolution of research within ABM in AEC field. The period from 1989 to around 2019 shows a marked increase in publication volume, highlighting a surge in academic interest and activity. The peak around 2023 suggests a spike in interest, likely spurred by significant technological breakthroughs such as advancements in computational power and the growing integration of digital tools like building information modeling (BIM) and digital twins. These technologies have facilitated more sophisticated simulations and analyses, attracting researchers’ attention to ABM applications in construction processes.

Furthermore, economic factors, including increased investments in construction and infrastructure projects globally, have also contributed to the rising trend in ABM publications. Regulatory pressures for sustainable construction practices and improved project efficiencies have motivated researchers to explore ABM as a viable tool for addressing these challenges.

To provide a comprehensive view of the growth, the analysis also breaks down the publication trends by various AEC subfields, including project management, sustainable design, and safety management. This disaggregation reveals that specific subfields, such as sustainable building design and construction safety, have experienced more rapid growth compared to others, indicating targeted areas of interest that align with industry demands and evolving research priorities.

Figure 7 illustrates a steady growth in publications within the top 10 academic journals from 1989 to 2024, showcasing sustained scholarly dedication and inquiry in our domain. This steady rise not only reflects a consistent academic commitment but also reveals the varied landscape of academic publishing. Some journals have been mainstays throughout this period, while others have seen their publication volumes vary, indicating shifts in research priorities or editorial directions. Notably, the Automation in Construction journal stands out for its significant contribution, consistently ranking at the forefront in terms of publication volume. Behind it, Sustainability and Building and Environment are also recognized for their impact.

The top 10 topics by count within our dataset, highlighted in Figure 8, form a crucial basis for the forthcoming analysis. These topics represent key areas of inquiry that have stood out in our research efforts, distinguished by their prevalence within the field. Their ranking, based on the frequency of their occurrence, offers a window into the dominant themes that permeate the literature, shedding light on the focal points of scholarly interest and investigation.

The distribution of the articles by country is illustrated in Figure 9, where the top countries are identified. The United States has the highest rank (32.8%), followed by China (27.1%), the UK (22.1%), and Germany (18%) regarding the number of publications in this area.

3.2. Content Analysis in Construction

In this subsection, we will focus on the application of ABM within the construction industry as illustrated in the mind map below (Figure 10).

3.2.1. Agent-Based Modeling in Project Management

ABM has emerged as a tool in project management, significantly enhancing the application of lean construction principles and efficiency optimization based on the literature classification in this domain as can be seen in Table 2.

Lean Construction

ABM plays a transformative role in simulating the behaviors and interactions of individual agents, workers, materials, or machinery, providing a lens through which the intricacies of construction processes can be examined and optimized [111]. This approach is particularly aligned with the principles of lean construction, which aim to minimize waste and maximize value through continuous improvement and efficient project management [112]. ABM stands out for its ability to capture the emergent properties of complex systems, allowing stakeholders to identify inefficiencies and potential improvements in a way that traditional modeling techniques cannot [113].

In the context of lean construction, the application of ABM facilitates a deeper understanding of the construction environment as a system of interconnected parts [114]. It enables the simulation of various scenarios to see how changes in one part of the system can affect the whole, providing invaluable insights into the potential impacts of lean interventions [115]. For example, ABM can help project managers to visualize the consequences of adjusting workflows, implementing new safety protocols, or introducing innovative material handling techniques [116]. This capability not only aids in the identification of potential bottlenecks and inefficiencies but also offers a predictive glimpse into the outcomes of specific lean strategies before they are put into practice [117]. Consequently, ABM serves as a vital decision-support tool, guiding the adoption and fine-tuning of lean principles in construction projects to achieve greater efficiency and effectiveness [118].

Furthermore, the flexibility and adaptability of ABM make it particularly suitable for the ever-evolving landscape of construction projects [119]. Each construction project comes with its own set of challenges, stakeholders, and environmental conditions, necessitating a tailored approach to lean implementation. ABM’s ability to model these unique project characteristics and simulate the complex dynamics at play allows for a customized application of lean construction principles [120].

Efficiency Optimization

The effectiveness of the ABM approach in pinpointing inefficiencies and streamlining processes is rooted in its ability to explore the effects of individual actions and choices on the broader system [3]. Through the detailed simulation of micro-level actions and interactions, ABM sheds light on complex phenomena that traditional top-down models might miss [121]. This ability to discern the subtle intricacies of complex systems positions ABM as a formidable instrument for boosting operational efficiency across various domains [122].

This methodology proves its worth across a wide array of applications, from enhancing supply chain and logistics operations to planning urban spaces and managing energy systems [123]. Decision-makers utilize ABM for its predictive prowess, allowing them to assess the potential impacts of different efficiency-enhancing strategies before actual implementation [124]. Such forward-looking analysis is crucial for refining processes, judiciously allocating resources, and minimizing waste. Furthermore, the inclusion of variability and adaptability in simulations mirrors the unpredictable nature of real-world systems, offering a grounded and practical framework for optimizing efficiency [6].

3.2.2. Construction Management and ABM

Process Planning

The ABM approach is integral for simulating complex logistics and operations, bridging gaps that traditional decision-support systems and algorithms encounter in construction engineering and management (CEM) [125]. ABM’s importance is underscored by its ability to model the intricate interactions and autonomous behavior of multiple agents within a construction process, such as trucks and trailers in logistics scenarios [2]. Unlike discrete event simulation (DES), which excels in sequential task modeling, ABM thrives in scenarios where tasks and interactions do not follow a linear sequence, making it exceptionally suited for logistics and supply chain management in offsite construction [126]. This adaptability allows for a more thorough understanding and optimization of construction processes, fostering a more efficient, flexible, and responsive planning environment [1].

The integration of ABM into offsite construction planning exemplifies a shift towards more agile and informed decision-making processes in the construction industry [1]. By accurately modeling the interactions and dynamics of various agents involved in construction logistics, ABM provides a foundation for developing pull-based simulation models that align closely with lean manufacturing principles [125].

Table 3 presents a systematic categorization of research on “Agent-Based Modeling (ABM) in Construction Management”. The research topics encapsulated within this table are segmented into three primary categories, as follows: (1) studies focused on utilizing ABM to manage complex logistics and operations within construction settings; (2) research dedicated to the dynamic simulation capabilities of ABM for process planning and safety management; and (3) investigations into the integration of ABM with material management and lean construction principles to optimize efficiency and process improvement.

While ABM’s applications in construction project management have demonstrated notable success in enhancing workflow optimization and resource allocation, practical implementation details are crucial to understanding its full potential. For instance, the use of ABM in simulating real-time logistics scenarios, such as the movement of materials and coordination between workers and machinery, provides clear, actionable insights that can streamline construction operations and reduce inefficiencies. Additionally, integrating ABM with sustainable construction practices addresses both environmental and operational concerns. By simulating energy consumption patterns and resource usage, ABM aids in identifying strategies for minimizing waste and optimizing energy efficiency, contributing to lower carbon footprints. However, the feasibility in solving the sustainability challenges posed by construction projects requires further investigation into the adaptability of ABM across different environmental conditions and project scales. This approach ensures that ABM is not only a tool for efficiency but also a catalyst for sustainable, environmentally responsible construction practices.

Execution Management

The integration of ABM execution management in the construction industry signifies a shift towards overcoming the constraints of traditional, centralized production systems [130]. Leveraging decentralized, multi-agent systems, ABM execution management introduces unprecedented levels of flexibility, agility, and resilience into construction project management [131]. Dynamic interactions among autonomous agents—representing different construction process elements like resources, orders, and products—ensure responsive and adaptable scheduling and execution control [20]. This approach enables construction projects to navigate effectively through complexities and uncertainties, fostering robustness against disruptions and enhancing the integration of production (re)scheduling with shop-floor execution [11]. Consequently, ABM execution management plays a crucial role in ensuring that construction projects meet individual requirements, adhere to stringent deadlines, and maintain superior quality in a highly competitive and unpredictable market environment [132].

3.2.3. Construction Industry Dynamics

Market Behavior

The construction market, with its intricate blend of product development, pricing strategies, and advertising decisions, often faces the challenge of integrating diverse models to make informed decisions [133]. This diversity, while beneficial in offering a wide array of perspectives, can also lead to complexities when disparate model results must be reconciled, requiring users to rely on their judgment to bridge these gaps. Such model complexity, whether real or perceived, emerges as a significant issue for users, alongside the inherent limitation of models to only account for responses recorded in historical data [134]. This limitation is particularly poignant in scenarios where the specific contexts behind purchase decisions are not well-documented, thereby obscuring the consumer’s decision-making process.

To address these gaps, the development and modeling of experiments incorporating contextual marketplace components have seen growth [135]. These experiments allow for control over elements such as shelf arrangements and marketing conditions, enabling researchers to delve into the impact of context on consumer behavior [136]. However, the scope of these models remains limited due to practical constraints on sample size and the level of contextual detail that can be feasibly incorporated into an experimental setting [137]. This limitation underscores the challenges traditional methods face in capturing the nuanced decisions and behaviors that occur within the complex systems of the marketplace [138].

ABM emerges as a novel approach in this context, offering a promising alternative to traditional statistical methods [139]. By simulating the behaviors of individual agents based on business-driven rules, ABM allows for the exploration of system-level outcomes from the bottom up [64]. This method is particularly suited for modeling complex systems such as consumer markets, where individual decisions contribute to overarching market trends [140]. ABM’s flexibility in handling various marketplace dynamics, including the interactions among competitors and the impact of multiple, simultaneous market moves, presents a significant advantage over conventional models [141].

Incorporating practical details, ABM can be effectively employed to model not only consumer behavior but also the intricate dynamics of the construction supply chain. By simulating how different stakeholders, such as contractors, suppliers, and consumers, interact within specific scenarios, ABM provides insights into decision-making processes that influence market behavior. For example, the application of ABM can illustrate how changes in pricing strategies or promotional offers affect consumer purchasing decisions in real-time. Additionally, ABM enables the exploration of various “what-if” scenarios, allowing stakeholders to understand the potential impact of different strategies on project timelines and resource allocation. This detailed modeling can help construction firms to anticipate market shifts, adjust their business strategies accordingly, and optimize resource utilization, thereby enhancing their competitive edge in a volatile market.

Figure 11 shows the interaction between market behavior, ABM, contextual experiments, and consumer behavior to illustrate the comprehensive approach of ABM in addressing market complexities and driving strategic decision-making. This diagram illustrates the cyclical and interactive process between the market behaviors, the role of ABM in simulating individual decisions that impact market trends, and the utilization of contextual experiments to provide insights into consumer behavior, which in turn influences strategic market decisions.

Agent-based modeling (ABM) in architecture, engineering, and construction (AEC) distinguishes itself from applications in social science or economics through its unique focus on the physical and logistical complexities inherent in construction projects. While ABM in social sciences often explores interactions among individuals or groups to analyze behavioral patterns and social dynamics, AEC applications emphasize the simulation of material flows, project timelines, and stakeholder interactions in a structured environment. AEC models incorporate specific parameters such as resource allocation, project constraints, and regulatory requirements, which influence decision-making processes. Additionally, the construction sector’s reliance on real-time data for site management and operations necessitates a more dynamic and responsive modeling approach compared to the relatively stable environments typically studied in social sciences or economics. This context-specific application of ABM in AEC allows for more tailored insights that address the industry’s unique challenges, such as optimizing resource use, enhancing collaboration among stakeholders, and improving project outcomes.

The application of ABM in the construction market can be particularly insightful, as it allows for the simulation of consumer behavior within specific retail environments, such as understanding the impact of store layouts on sales or exploring market-level purchasing trends to enhance organizational profitability [142]. For instance, models like the “SimStore” simulation offer insights into how consumers navigate retail spaces, impacting product placement and store sales strategies [143]. Similarly, market-level ABM efforts focus on broader purchasing patterns, enabling companies to tailor their strategies to better meet consumer demands and preferences [144].

The Virtual Market Learning Laboratory exemplifies the comprehensive application of ABM in understanding consumer markets [145]. This large-scale model simulates the shopping behavior of consumer households and the business strategies of retailers and manufacturers, providing a detailed overview of the interactions within a national consumer market [146]. Through such simulations, ABM offers a good understanding of the market, allowing for the exploration of innovative strategies in product placement, pricing, and advertising that are grounded in the complex realities of consumer behavior.

In the context of architecture, engineering, and construction (AEC), validating and verifying agent-based modeling (ABM) models are critical to ensuring their reliability and applicability. The conducted research has validated the ABM models by comparing the simulated outcomes with empirical data collected from real-world scenarios in the construction industry, ensuring that the models accurately reflect actual behaviors and trends. Additional verifications could involve testing the models through various scenarios to confirm that they function as intended and produce consistent results under different conditions. Engaging with industry professionals throughout this process could further enhance the model’s credibility, as their insights help to refine assumptions and ensure that the models capture the complexities of real-world construction dynamics effectively.

Supply Chain Management

The excavation and subsequent stockpiling of materials such as sand, gravel, rock, and clay play a crucial role in the construction process, often leading to an excess of materials that are either reused or disposed of [147]. The handling and optimization of these materials not only have significant economic implications but also impact the environmental footprint of construction activities [148]. The process involves excavating materials, stockpiling them on-site, and later using them to fill the areas. However, challenges arise due to factors like high holding costs, limited space, and the potential degradation of materials by rainwater, leading to a surplus of backfill that must be managed efficiently [149]. The practice of exporting materials to other sites or landfills, while economically viable, contributes significantly to construction waste, highlighting the need for improved recovery and recycling practices to enhance both cost-effectiveness and environmental sustainability [150].

However, the reuse and recycling of backfill materials encounter several obstacles, including the lack of coordination among various construction sites operated by different firms and the dynamic nature of the supply chain for shipments [151]. The situation is further complicated by the varying operational states of construction sites, which can shift between excavation and backfilling, and the absence of a unified approach to manage these changes effectively [152]. Through the exploration of centralized and distributed modeling paradigms, including ABM, the optimal strategies for managing the dynamic supply chain of materials can be identified, thereby improving waste recovery efficiency across construction sites and setting a foundation for future research on complex supply chain structures in a project-based environment.

ABM serves as a foundational approach in simulating the decision-making processes of various stakeholders within the material supply chain [153]. These stakeholders, including producers, consumers, landfills, and commercial sources, each operate based on their unique objectives and constraints, engaging in negotiations to reach a consensus on backfill shipments. This simulation constructs the supply chain as a multi-agent system where autonomous agents represent the operational and decision-making dynamics of business entities [154]. These agents, embodying construction sites, landfills, and commercial sources, interact within a defined framework to simulate real-world interactions and decision-making processes. The construction site agent, for instance, represents the various phases a site undergoes, from excavation and backfill exportation to later stages requiring materials importation [155].

3.2.4. Construction Safety

The construction industry has been historically marked by its concerning safety statistics, underscoring a critical need for enhanced safety protocols and accident prevention strategies [156]. In the United States, a striking 991 fatal injuries were recorded in 2016, the highest in a decade, overshadowing other industries significantly [157]. This trend is not isolated; in the United Kingdom, the construction sector, while only employing 5% of the workforce, was responsible for nearly 30% of fatal injuries [158]. Similarly, China’s construction industry led in fatalities, with 3806 deaths in the same year, highlighting a global issue of worker safety [159]. These alarming figures not only emphasize the dire risks faced by construction workers but also the considerable social and economic losses incurred, propelling accident prevention to the forefront of construction management improvement efforts. By exploring the literature, we were able to identify two areas where there could be high potential to integrate ABM, as can be seen in Table 4.

Worker Behavior Modeling

Based on the literature, it is evident that the influence of management behaviors on worker safety in construction projects is a multifaceted issue that has garnered significant attention [167,168,169]. Previous studies have underscored the critical role of management in shaping the safety culture and practices on construction sites. For instance, the behaviors and operational tactics of safety officers, supervisors, and senior managers are pivotal in creating an environment that prioritizes safety. Safety officers are primarily responsible for monitoring compliance with safety protocols and conducting regular safety training, while supervisors directly influence workers’ daily safety practices by setting examples and enforcing safety rules [170]. Senior managers, on the other hand, are crucial in integrating safety objectives with production goals, thereby ensuring that safety is not compromised for the sake of productivity [171]. Despite the acknowledged impact of these roles, there remains a challenge in quantifying and systematically understanding the direct effects of specific managerial behaviors on safety outcomes due to the complex nature of construction projects and human behaviors.

ABM allows for the simulation of complex systems composed of interacting agents, making it particularly suitable for modeling the intricate dynamics of construction site safety [172]. By representing different management roles and workers as agents with specific behaviors, ABM can provide insights into how these behaviors influence overall safety performance on construction sites. This modeling approach can simulate real-world interactions and scenarios, enabling researchers to observe the outcomes of various management strategies in a controlled virtual environment. Additionally, ABM can facilitate the exploration of “what-if” scenarios, assessing the impact of changes in management behaviors on worker safety in a way that is not feasible in the real world [173]. This ability to model and analyze the nuanced interactions between management actions and worker responses offers a promising avenue for developing targeted interventions that can effectively enhance safety outcomes in the construction industry.

Accident Prevention Strategies

ABM offers a dynamic framework for integrating proximity detection technologies to enhance accident prevention on construction sites. Drawing from diverse technologies like RFID, GPS, and magnetic sensing, ABM can simulate the interactions between workers, machinery, and environmental variables in real-time scenarios [174,175]. For instance, ABM can incorporate the principles behind the HASARD (Hazardous Area Signaling and Ranging Device) system, (U.S. National Institute for Occupational Safety and Health (NIOSH), Washungton D.C. USA) which uses magnetic sensing to alert workers when they approach hazardous areas. This predictive capability extends to systems that utilize RFID and GPS for real-time location tracking, providing a comprehensive view of the construction site’s dynamics.

Moreover, ABM can provide data from advanced technologies, such as UWB (ultra-wideband) systems for real-time localization with high precision and video/image devices for monitoring site activities, to create detailed simulations of construction site operations [176,177]. In addition, integrating a blockchain-based information management framework can further enhance ABM’s application in construction safety by ensuring the secure and transparent management of safety data, thereby supporting real-time decision-making for accident prevention [178]. This approach allows for the testing of different safety interventions in a virtual environment, enabling safety managers to visualize the impact of deploying various proximity warning systems and to assess their potential in reducing equipment-related collisions.

3.3. Content Analysis in Architecture

3.3.1. Energy Efficiency and Occupant Well-Being

ABM is increasingly utilized to study the behavior of individuals within buildings, focusing on energy and indoor-environmental performance [179,180]. This approach simulates various scenarios including transportation, pedestrian movement, and evacuation, but specifically here, we concentrate on occupant-centric applications for building performance. Selected studies provide insights into how people and their environments are represented, emphasizing the importance of domain knowledge and computational tools for effective ABM. Surveys and interviews often precede ABM development to gather essential data on occupant behavior, with some research incorporating established theoretical frameworks to model comfort levels and behavioral responses [181,182]. ABM has demonstrated practical applications in enhancing energy efficiency and occupant well-being through various case studies. For instance, a study on a university campus utilized ABM to optimize energy consumption by simulating occupant behavior in response to different building configurations and energy management strategies. The results revealed that occupant engagement in energy-saving behaviors could lead to significant reductions in overall energy use. Another example is a smart city initiative in Barcelona, where ABM was employed to model urban mobility and building energy performance, aiding city planners in developing strategies to enhance energy efficiency while improving residents’ quality of life.

However, integrating ABM with building management systems (BMS) presents challenges. Data interoperability between ABM and BMS can be complex, as these systems often rely on different data formats and protocols. Additionally, real-time data acquisition and processing require advanced computational capabilities that may not be readily available in all buildings. Implementing ABM on a large scale necessitates overcoming these challenges by developing standardized data protocols and robust computational infrastructures. Such advancements could facilitate the widespread adoption of ABM in energy performance optimization and urban planning, driving substantial improvements in both energy efficiency and occupant well-being.

Representations of occupants and their interactions with building systems highlight varied approaches to decision-making and behavior modeling [183,184]. Studies explore how occupants interact with windows, cooling systems, and other building elements, often influenced by energy-conscious training or predefined behavioral models [185,186]. Decision-making theories like the Theory of Planned Behavior and the Belief–Desire–Intention framework are applied to understand how occupants make choices regarding their environment, factoring in attitudes, norms, and control beliefs [179]. These models account for daily habits, environmental responses, and the social dynamics of occupant interactions, offering detailed insights into the factors driving energy consumption and environmental adjustments within buildings.

In the exploration of ABM for understanding building performance, a variety of computational tools and software environments play a pivotal role in crafting realistic simulations of occupants, their environment, and the complex interactions between them [179]. For modeling human behavior within buildings, several tools stand out due to their specialized capabilities. NetLogo, an open source, multi-agent programming environment, is widely used for its flexibility in defining diverse agent behaviors and interactions [187]. Similarly, AnyLogic 8.9.2 offers a commercial solution for detailed agent behavior modeling across various scenarios [188]. Other tools like the Occupancy Simulator and Repast Symphony offer unique features, such as web-based interfaces for occupant behavior simulation and complex adaptive systems modeling, respectively [189]. MATLAB R2024b, and the PMFserv platform are also notable for their application in ABM solutions, highlighting the diversity of tools available for researchers [180].

In exploring the applications of agent-based modeling (ABM) for energy efficiency and occupant well-being, it is essential to consider the integration of machine learning and AI-driven optimization strategies. For instance, a recent study [190] demonstrated how advanced algorithms can enhance predictive capabilities related to building energy demand. By leveraging machine learning techniques, researchers can analyze vast datasets to identify patterns that inform energy management strategies, ultimately leading to more efficient building operations. Additionally, a recent report [191] highlighted the critical role of infrastructure and connectivity in urban development. This work underscored how physical and social barriers can impact energy consumption behaviors and community engagement in sustainability initiatives. Integrating these insights into ABM frameworks can provide a more comprehensive understanding of how occupant behaviors are influenced by both technological advancements and urban infrastructure challenges, thereby enhancing the effectiveness of strategies aimed at improving energy efficiency and occupant well-being. By addressing these factors, ABM can better simulate real-world conditions, paving the way for more effective interventions in building performance and urban planning. The simulation of the built environment within ABM studies employs different software to accurately represent buildings and their systems. EnergyPlus 24.2.0 emerges as a popular choice for its comprehensive simulation of buildings’ energy performance, complemented by graphical interfaces like OpenStudio 3.8.0 and DesignBuilder v7.3 [192]. Other software like eQuest 3.65.7175 and TAS 9.5 provide alternative methods for energy and thermal analysis, demonstrating the range of tools that can be used to model the physical conditions within buildings [193]. Additionally, the Radiance lighting simulation engine illustrates the capacity to model visual environments, emphasizing the importance of integrating various environmental aspects into ABM studies [73].

3.3.2. Facility Management

In the maintenance and repair sector, the focus is on preempting system failures, minimizing the response time to maintenance issues, and ensuring serviceability during repairs to avoid financial losses and user dissatisfaction [194]. ABM, often complemented by sensing technologies and other analytical tools, has proven effective in developing frameworks that enhance the maintenance and repair decision-making process [195]. For instance, studies have integrated ABM with building information modeling (BIM) and sensing technologies to capture real-time data throughout a facility’s lifecycle, optimizing maintenance decisions [195]. Similarly, the application of ABM with sensing technologies and game theory has led to the development of collaborative platforms that support maintenance decision-making, showcasing the model’s utility in streamlining operations for facility managers, service providers, and repair technicians [195].

Energy consumption management has also benefited from the application of ABM, through the simulation of diverse and dynamic human behaviors in relation to various facility systems and appliances [73]. These studies have explored energy-saving strategies and policies across different facility types, assessing the impact of governmental incentives on energy efficiency and examining the balance between reducing energy consumption and maintaining occupant comfort [196]. Innovative ABM approaches have enabled the development of multi-objective models that not only aim for energy efficiency but also consider occupant comfort, thereby promoting a more holistic approach to facility management [197]. Furthermore, the general facility management research has extended to civil infrastructures, providing ABM to simulate complex systems and their interdependencies, thus enhancing decision-making processes and operational efficiency across multiple infrastructure sectors [198].

3.4. Integration with Emerging Technologies

3.4.1. Three-DimensionalPrinting

In the course of a literature review focusing on the integration of ABM within the construction industry, particularly in utilizing mobile robots for 3D printing applications, several pivotal findings emerge. Firstly, the literature underscores ABM’s inherent ability to simulate complex interactions and operational dynamics of mobile robots in construction settings [82]. Studies highlight how ABM serves as a critical tool in understanding and optimizing the behavior of robots engaged in concrete and steel printing processes [199].

Secondly, this review reveals a significant gap in existing research concerning the practical application of mobile robots for 3D printing in construction, particularly in the fabrication of reinforced concrete elements [200]. The absence of comprehensive studies or real-world implementations underscores the innovative potential of ABM in this field [6]. Through ABM, researchers are able to construct detailed simulations that explore the feasibility, efficiency, and possible configurations of robotic construction methods [201].

Furthermore, the literature consistently emphasizes the meticulous approach required in the development of ABM simulations, particularly in defining the scope and detailing of the model [202]. This involves careful consideration of which entities, activities, resources, and interactions to include, ensuring that the model accurately reflects the complexity of the construction process [203].

3.4.2. Life Cycle Assessment (LCA) and ABM

In the domain of environmental studies, ABM is a tool with several critical applications, distinguished by its ability to simulate complex dynamics and behaviors [38]. ABM is primarily utilized for capturing spatial and market dynamics and integrating irrational and social behaviors into environmental analyses [204]. This multifaceted application enables researchers to simulate various system configurations and assess the impact of different scenarios, such as government incentives or environmental constraints on behaviors like beverage consumption [205]. Moreover, ABM’s ability to model spatial and temporal dynamics offers insights into the environmental impacts of urban development and product introduction, illustrating how market dynamics and spatial configurations significantly influence environmental outcomes [10]. Such dynamic simulations, often complemented by life cycle assessment (LCA), provide an understanding of the environmental implications of various policies and consumer behaviors, underlining ABM’s role in capturing the complexity of environmental interactions [206].

The construction of ABM within LCA involves the modeling of cognitive agents with decision-making capabilities, representing individuals or entities such as households, firms, or governmental bodies [207]. These agents, whether focusing on product consumption or policy analysis, embody the decision-making processes influencing environmental impacts [208]. The interaction among cognitive agents, technological agents, and the static elements of a supply chain forms the backbone of the decision-making process within ABMs [209]. For instance, the deployment of green buildings is influenced by the interplay between governmental incentives, public perception, and developer actions, showcasing how agent interactions drive environmental decisions [205]. This intricate modeling of agent interactions highlights ABM’s unique ability to simulate the complex web of decisions that shape environmental outcomes [210]. Figure 12 presents a timeline of a product’s life cycle, from resource extraction to end of life, highlighting key ABM outputs at each stage. It illustrates how each stage contributes to different market dynamics, such as market share, supply chain organization, spatial dynamics, consumption patterns, and temporal dynamics.

3.4.3. Digital Twin Integration

Agent-based simulations have been a part of various fields for many years and have found applications in transportation over the past two decades, with MATSim and SimMobility being notable examples [201]. Traditional transportation modeling has largely focused on analyzing travel as flows between areas [211]. However, agent-based simulation offers a shift towards integrating the benefits of activity-based modeling and dynamic assignment [212]. This method allows for the exploration of emergent phenomena that arise from the interactions of individual agents, which traditional models often overlook [213].

The essence of agent-based modeling lies in its ability to capture the fundamental aspects of human behavior within transportation systems [76]. Digital twins aim to replicate the behavior of real-world objects without compromise, extending from the micro atomic to the macro geometrical level [214]. While it may seem challenging to align the detailed aspirations of digital twins with the broader strokes of agent-based simulations, transportation models treat individuals as the basic units of analysis [215]. This alignment suggests that for transportation planning, the detailed replication of every atomic level detail is less critical than capturing the relevant behaviors and choices of individuals [216]. This approach to modeling emphasizes the importance of relevant data, such as location, mode of transport, and trip purpose, in creating accurate representations of traveler behavior [216].

In buildings and construction management, integrating agent-based modeling (ABM) with digital twin (DT) technologies presents a transformative approach to simulate, analyze, and optimize complex interactions within built environments [217]. This integration enables the creation of dynamic, real-time digital replicas of physical buildings, where individual agents (representing components such as occupants, HVAC systems, or construction resources) interact within the DT framework [218]. Such a setup allows for the exploration of emergent behaviors and system-wide impacts of localized changes, offering insights into operational efficiency, energy consumption, and occupant comfort [217]. ABM helps in addressing challenges like predicting the outcomes of various design and operational decisions, enhancing resource allocation, and improving the overall sustainability and resilience of building projects [1].

In addition, with an infrastructure equipped with sensors and local intelligence, smart cities are poised to bridge the gap between digital twins and agent-based models further [77]. These technologies enable real-time adaptation to changing conditions, such as traffic light adjustments based on actual traffic flows [219]. The integration of smart technologies introduces a dynamic where both the city’s infrastructure and its inhabitants adapt to each other, creating a complex system of interactions [220]. This evolution poses questions about equilibrium and computational demands, underscoring the need for simulations that can navigate these complexities [221].

An important point here is that methods like discrete event simulation (DES) [126], system dynamics (SD) [222], finite element analysis (FEA) [223], and computational fluid dynamics (CFD) [224] offer specialized insights into system operations, structural behaviors, and fluid dynamics. However, ABM distinguishes itself by its unique ability to simulate complex systems at an individual agent level, capturing the interactions and emergent behaviors that these other methods may not fully address [2]. ABM’s granular focus on individual entities and their decision-making processes allows for a dynamic and flexible exploration of system behaviors, making it particularly adept at revealing the intricate patterns and potential outcomes arising from simple rules of interaction [20]. This adaptability and the capacity to model emergent phenomena make ABM a versatile and powerful tool in DT environments, especially when analyzing systems where individual behaviors and interactions significantly influence the overall dynamics, such as in urban planning, social sciences, or ecological systems [225].

To give an example here, DES can be used to manage elevator operations during peak hours in an office building. In this scenario, each event could represent an elevator arriving at a floor, the doors opening/closing, and people entering or exiting [226]. The simulation focuses on the sequence of these events and their timing, aiming to optimize the flow of people by minimizing wait times and avoiding overcrowding [227]. The model might adjust variables such as elevator speed, frequency, and capacity based on predefined schedules and average occupancy rates [228]. However, DES would treat passengers as collective entities responding to these events rather than as individuals with distinct behaviors [229].

On the other hand, using ABM for the same scenario involves creating agents representing individual building occupants with unique characteristics, such as their starting floor, destination, and even preferences for taking stairs versus waiting for an elevator [179]. The model simulates the decision-making process of each agent, which could include factors like impatience thresholds leading some to choose stairs if the wait time exceeds a personal limit [230]. ABM allows for the emergence of complex behaviors from simple rules, such as the formation of queues or changes in peak usage times as agents adapt to system constraints [231]. Table 5 summarizes a series of research studies focused on the integration of ABM within the digital twin framework across different facets of building and infrastructure management. Each study explores the potential of ABM to enhance areas such as building management, construction project management, and infrastructure resilience by simulating real-world dynamics and interactions.

3.4.4. BIM Collaboration

Building information Modeling (BIM) represents a progressive 3D modeling technology that offers comprehensive insights to professionals in architecture, engineering, and construction, aiming to enhance building systems’ efficiency [239]. Currently, BIM’s effectiveness is further bolstered by building performance simulation (BPS) tools, such as EnergyPlus and OpenStudio, which aim to elevate construction quality while minimizing environmental impacts through advanced technical expertise [240].

Despite its advantages, the application of BPS in evaluating building performance faces challenges, especially in accurately reflecting real-world conditions. Common BPS tools often rely on predetermined settings and fail to account for the variability in occupant behavior and environmental interactions. Achieving precise building performance assessments necessitates simulations under realistic conditions, including the detailed modeling of human perception [241]. Errors in BPS tools frequently stem from incorrect inputs related to occupants’ profiles and building operations [242]. Most BPS tools depict occupants through static schedules, overlooking the dynamic interplay between building systems and human activity. Recognizing the impact of occupancy on actual energy use and indoor performance is crucial, necessitating a shift from static to dynamic modeling approaches to capture the nuanced effects of occupant behavior and environmental variables on building efficiency [243].

In response to these limitations, recent research has explored occupant behavior modeling through innovative methods like ABM and system dynamics (SD) [244,245]. ABM allows for the detailed simulation of individual and group behaviors within buildings, offering insights into the stochastic nature of human actions.

3.4.5. Machine Learning

The intersection of machine learning (ML) and agent-based modeling (ABM) is revealing how various ML methodologies—supervised, unsupervised, semi-supervised, and reinforcement learning—augment ABM applications [246]. Notably, the literature distinguishes evolutionary computation algorithms, like genetic algorithms (GA) and particle swarm optimization (PSO), as optimization-centric computational intelligence that does not rely on training data, hence aligning more with meta learning optimization [247].

The elucidation of ML’s impact on ABM spans simulation and optimization, highlighting the necessity of substantial data to train ML models [248]. Integrated simulation-optimization frameworks are proposed for enhancing situational awareness, predicting agent behavior, and aiding decision-making processes. For example, Augustijn et al. categorize ML applications in ABM across different stages: preprocessing, agent-behavior prediction, decision-making, and postprocessing [249]. They outlined a progression where ML algorithms are initially used to inform ABMs, replacing rule-based inputs, followed by agent behavior predictions for decision-making, and finally the utilization of data post-ABM run for model calibration or validation.

Researchers segment ML’s functionalities within ABM into two main roles: enhancing agents’ situational awareness through prediction and pattern recognition, and reinforcing agent behaviors for strategic interventions [20]. Four specific scenarios are identified, namely (1) microagent situational awareness learning, (2) microagent behavior interventions, (3) macrolevel emergence emulation, and (4) macro ABM decision-making. These scenarios are further dissected to discern at which level ML is utilized (micro or macro) and its role within the ABM framework. Additionally, researchers categorize ML applications in ABM into computing and non-computing science domains, emphasizing the behavior model and decision-making process primarily in the latter, which includes diverse fields like social behavior analysis and health care (Figure 13) [20].

Moreover, reinforcement learning (RL) is designed to optimize decision-making processes by interacting with an environment to achieve the highest cumulative reward [250]. Through these interactions, RL agents can identify the most effective actions within a given context to enhance their overall performance [251]. The core of RL revolves around reward feedback, which is crucial for the agent to adapt and refine its behavior [20,252], as illustrated in Figure 14.

RL operates through an agent, shown as an Android, engaging with an environment, like a maze, where its decisions are driven by a Markov decision process (MDP). The agent’s actions are informed by the state and reward feedback from the environment, ensuring a continuous learning loop. An observer oversees this process, monitoring the state transitions within the environment, which adds an analytical dimension to the RL system. This interaction between the agent’s actions, the environmental response, and the MDP’s guidance is pivotal, as it forms a feedback loop that allows the agent to learn and adapt its behavior to maximize cumulative rewards, illustrating the iterative and dynamic nature of RL.

RL algorithms are broadly categorized into three distinct families, each with a specific focus. The first family employs algorithms for value iteration (VI), which use a model as a value approximator to correlate states with cumulative rewards [253]. The second family focuses on policy iteration (PI), where the model acts as a policy approximator, mapping states directly to optimal actions [254]. In this context, value-based algorithms are often termed critic-based [255], as they estimate the rewards for different states, while policy-based algorithms are referred to as actor-based, focusing on determining the best action from the current state [256]. The third family encompasses actor–critic methods that execute generalized policy iteration (GPI), incorporating both value and policy approximators [257]. These actor–critic methods represent a synthesis of the two approaches, aiming to leverage the strengths of each.

Figure 14. Components and flow of information in a typical reinforcement learning system using a Markov decision process (MDP) framework based on [20,258,259,260].

3.4.6. Hybrid Simulation Models

Within the domain of building occupancy simulation, a plethora of models are employed, with agent-based and graph-based models standing out due to their widespread use [261]. Agent-based models are typically utilized for detailed, micro-level simulation, capturing intricate interactions and emergent behaviors among occupants. Conversely, graph-based models excel at a macro level, modeling large populations efficiently, albeit with less detail [262]. The choice between microscopic simulations, which afford granular insight into individual interactions, and macroscopic models, preferred for their lower computational demands, is dictated by the specific needs of the simulation task [263].

The dichotomy between agent-based and graph-based simulations is pronounced in their operational focus [264]. Agent-based simulations concentrate on the properties and interactions of individual agents, creating a computationally intensive environment as the number of occupants increases. On the other hand, graph-based models, while less resource-intensive, lack the ability to capture the behaviors that emerge from detailed occupant-environment interactions. Therefore, the decision to use one model over the other hinges on the intended outcome of the simulation—whether it is to analyze the nuanced behavior of occupants in a detailed setting or to efficiently simulate occupancy dynamics on a larger scale.

The adoption of hybrid models represents an innovative solution to the limitations of pure agent-based or graph-based approaches [210]. These models integrate the strengths of both, allowing for detailed agent-based simulation in certain areas while leveraging the computational efficiency of graph-based modeling in others.

3.4.7. Open Source and Collaborative Platforms

Open source ABM tools are increasingly being recognized as a valuable asset within the architecture, engineering, and construction (AEC) sector [265]. The advocacy for and development of such tools, such as cppyABM v0.9.1 [266] and MUSE 4.4.3 [267], are propelled by a collective aspiration to democratize access to advanced simulation technologies [268]. By making these tools freely available, researchers and practitioners across the globe can partake in the iterative refinement of models, contributing to a body of knowledge that benefits the entire industry. This openness not only accelerates innovation but also fosters a culture of transparency and reproducibility in research. In the context of AEC applications, open source ABM tools can enable more sustainable design decisions, optimize construction operations, and enhance the lifecycle management of built assets. The collaborative nature of open source projects often leads to tools that are more versatile and robust, as they are shaped by a diverse array of user experiences and expert insights.

The collaborative model development in ABM is another area that is gaining traction within the construction domain [269]. This approach brings together professionals from different disciplines and organizations to contribute to a unified modeling project. The synergy of expertise from architects, engineers, construction managers, and other stakeholders leads to models that are not only more comprehensive but also reflective of the multifaceted nature of construction projects. Collaborative ABM development supports the creation of models that encapsulate the complexity of real-world scenarios, thereby improving the accuracy and utility of simulations [270]. These collaborations are often facilitated by platforms that support version control and real-time communication, allowing team members to work synchronously or asynchronously towards a common goal. The co-creation process encourages knowledge exchange, ensuring that the resulting models are well-informed by the latest industry practices and scientific research.

4. Discussion

This section is structured in two main parts: initially, it revisits the key outcomes derived from the literature review; subsequently, it explores the identification of prevailing gaps in the existing studies, offering directions for future research endeavors to bridge these gaps.

4.1. Evolution and Trends in Publication

While ABM has been widely acknowledged and implemented in diverse fields such as biology, sociology, politics, and economics, its adoption in the construction sector is relatively recent, particularly when compared to more traditional simulation methods like system dynamics (SD). This shift reflects the growing recognition of ABM’s potential in addressing complex, dynamic systems inherent in construction projects. The increasing number of publications focusing on ABM in construction, driven by advancements in computing technology, marks a critical step forward. However, despite the rise in interest, ABM is yet to fully realize its potential within the construction industry, leaving substantial room for future research and practical applications.

The trajectory of ABM research in construction has evolved from early attempts to develop broad, multiphase models—often with limited direct applicability—to more recent efforts that focus on specific, practical models. However, these recent studies still lack the practical maturity required for direct implementation in the construction industry. This gap highlights the need for continued research aimed at refining ABM models to ensure that they can be effectively applied in real-world scenarios.

This review of 178 publications across various sources underscores ABM’s expanding relevance in construction. There is clear evidence of a growing research community focused on ABM, with applications extending into new areas within the construction sector. Notably, labor management and building operations have attracted particular interest. This expanding scope signals ABM’s potential for addressing complex challenges in these areas, further establishing its significance in the industry. The rising number of publications also points to a strong foundation for future interdisciplinary collaborations, as researchers from various specializations contribute to the growth of ABM applications.

This review identified some highly cited authors and several key figures in the field of agent-based modeling, within the architecture, engineering, and construction industry. Prominent authors like Khodabandelu and Park [1,195], DeAngelis and Diaz [3], and Raoufi and Fayek [11] have significantly contributed to the application of ABM in construction and decision-making processes. Moreover, Antosz et al. [4] highlighted broader challenges and tasks related to complex systems that are crucial in shaping ABM methodologies. For example, Holman et al. [173] examined computational modeling in ergonomics, while Berger and Mahdavi [179] explored ABM applications in building performance analysis. These findings provide a comprehensive overview of the field’s evolution and allow for tracking the research frontiers of ABM applications, particularly in interdisciplinary contexts.

In summary, the expanding scope of research, coupled with the contributions of influential authors, provides a comprehensive overview of ABM’s evolution in construction. Although significant advancements have been made, the field is still in its developmental phase, and there remains ample opportunity for ABM to become more integrated within the construction industry. Future research should prioritize the refinement of practical models and foster interdisciplinary collaborations to fully unlock ABM’s potential in this domain. Finally, to expand the discussion on the technical aspects of agent-based models (ABM) within architecture, engineering, and construction (AEC) applications, it could be interesting to consider the potential integration of big data from social networks, such as the approaches discussed by Thai at al. [271]. In fact, incorporating such data could significantly enhance ABM models by providing real-time, large-scale behavioral insights. This would allow for more nuanced simulations in urban development and community engagement, leading to more adaptive and informed decision-making in sustainable AEC practices.

4.2. Future Research Directions

The exploration of ABM in the development of novel construction methodologies reveals significant research gaps. Current practices have yet to fully capitalize on ABM’s potential to simulate complex workflows and optimize building processes. There is a lack of in-depth studies on the application of ABM to innovative building techniques such as autonomous construction sites, which could lead to smarter and more efficient practices. There is a pressing need for comprehensive research that not only investigates ABM’s ability to enhance construction methodologies but also its role in the transition to automation and intelligent material management within the industry.

In the realm of sustainability and resilience, ABM’s application in construction is still in its nascent stages. Research has not extensively explored how ABM can advance green building techniques or assist in disaster resilience. There is a substantial research gap in understanding how ABM can be effectively utilized to create buildings that are both environmentally sustainable and resilient to disasters. Future research must address these gaps by developing ABM frameworks that can intricately model the interplay between ecological sustainability, resource management, and resilience strategies against natural disasters.

Technological integration with ABM in construction also presents numerous research opportunities that are yet to be fully explored. The synergies between ABM and emerging technologies such as IoT, AI, and blockchain have been hypothesized, but detailed studies are lacking on how these integrations can be achieved and the impact they can have on construction processes. The potential for ABM to work in conjunction with real-time data inputs, predictive analytics, and secure supply chains is immense, yet the research community has not fully investigated these integrations. Future studies must delve into how these technologies can be interwoven with ABM to deliver more precise, efficient, and accountable construction practices.

Although there has been notable progress in the application of ABM within the AEC sector, especially in the last five years, its maturity level is still evolving. This research highlights significant gaps in the existing literature where ABM holds potential for impactful future research. The concentration of research on popular themes has inadvertently led to the neglect of other promising areas. For example, while significant effort has focused on optimizing design for evacuation scenarios, less attention has been paid to improving designs for day-to-day operations, energy efficiency, and occupant comfort. These areas, crucial for the routine functionality and sustainability of buildings, represent significant opportunities for future research to explore, balancing the emphasis between emergency preparedness and operational efficiency.

Despite the broad application of ABM in AEC, cutting-edge research areas, such as 3D printing optimization, energy management in green buildings, and automation in smart buildings, remain underexplored. These innovative domains offer ground for deploying ABM to enhance construction processes and outcomes. Moreover, current ABM studies in construction often lack inclusiveness, focusing narrowly on specific aspects of labor productivity or safety, without considering the complex interplay of factors that influence real-world outcomes. Furthermore, addressing equity and inclusiveness in infrastructure projects through ABM could enhance social sustainability, especially in underrepresented areas of construction research. Developing frameworks that integrate ABM with principles of equitable resource distribution and accessibility [272] would provide a comprehensive approach to promoting fairness within construction processes. Future research needs to develop more holistic models that account for a broader spectrum of laborer characteristics and behaviors, as well as designs that consider multiple types of incidents and their implications for building operations and evacuations.

In addition, the influence of varying contextual factors such as site-specific conditions, workforce diversity, and regional safety regulations on ABM applications is an area deserving of further research. These factors can significantly impact the generalizability of ABM outcomes, especially when applied across different construction scenarios. Conducting a sensitivity analysis or implementing comparative case studies would provide deeper insights into how these contextual differences shape ABM effectiveness in construction processes. However, due to the complexity and scope of such an investigation, a separate, dedicated research project would be preferable for a more rigorous analysis. Future studies could benefit from this approach, adding a robust layer of validation to ABM applications within the construction industry.

The scarcity of generalized, open source platforms for ABM in AEC hinders the efficient advancement of research in this field. Future efforts should aim at creating accessible, customizable platforms that encapsulate diverse behavioral and operational aspects of construction projects. Additionally, integrating ABM with other simulation techniques and technologies, such as building information modeling (BIM), sensing technologies, and stochastic approaches, can unlock new potential for research and practical applications. However, these hybrid approaches also raise challenges related to computational demands and real-time data integration. Finally, there is a pressing need for the empirical validation of ABM models to ensure their relevance and applicability to actual construction scenarios, calling for research that bridges theoretical models with real-world data and practices.

As we look to the future, the application of ABM in AEC presents a landscape filled with uncharted territories. While ABM’s promise for improving AEC processes is acknowledged, the research is still limited when it comes to implementing these models in practice, especially in developing prescriptive models that offer tangible solutions. The industry’s slow adoption of these innovative strategies indicates a gap between ABM research and its practical application. There is a critical need for research that not only conceptualizes but also pilots and validates new ABM-driven construction paradigms, propelling the industry towards more sustainable, efficient, and technologically advanced practices.

5. Conclusions

ABMs are increasingly being recognized for their ability to encapsulate the complexities inherent in the lifecycle of buildings, spanning from design and planning through to construction and operation. The growing body of academic literature reflects an expanding interest in the field, yet the practical adoption of ABMs within the industry still faces significant hurdles. These challenges span educational, methodological, technical, and accessibility dimensions, necessitating concerted efforts to integrate ABMs into the mainstream of architectural and engineering education, enhance their interoperability with established workflows, and improve the transparency and accessibility of research findings. This paper contributes to these efforts by surveying existing ABM implementations in AEC, drawing on an analysis of 178 documents.

In addition, it integrates ABM studies within the architectural domain, acknowledging the field’s interdisciplinary nature. The entity-based classification framework proposed facilitates a cross-disciplinary synthesis of architectural research, addressing the challenges of domain-specific literature retrieval and promoting a more precise definition and description of agents and models. This precision is increasingly critical as ABMs evolve to address the architectural process’s complexity through diverse agent categories. This classification aims to guide both future research directions and practical applications of ABMs in architecture, advocating for clear entity descriptions to support reproducibility and cross-disciplinary collaboration within the AEC sector.

Recommendations for integrating ABM with complementary technologies like AI, digital twins, and BIM for enhanced visualization and expanding ABM applications to include equipment operations and theoretical behavior models are also discussed. Despite these insights, this review acknowledges its own limitations, such as the exclusive analysis of specific databases and the omission of certain bibliometric metrics. It calls for future, more specialized reviews to keep pace with the rapidly expanding body of ABM research, suggesting that more focused and in-depth analyses could further refine the application of ABMs in construction, particularly in the design phase.

Funding

The author would like to acknowledge the support of Prince Sultan University, RIC Research and Initiative Center, SALab Sustainable Architecture Laboratory for the article processing charges (APCs) and incentive financial supports forthis publication.

Data Availability Statement

Data are available at Prince Sultan University SALab Sustainable Architecture Lab, Riyadh, Saudi Arabia.

Acknowledgments

The author would like to acknowledge the financial support of Prince Sultan University, CAD College of Architecture and Design, SALab Sustainable Architecture Laboratory, and RIC Research and Initiative Center for providing a collaborative environment that support research and publication outcomes.

Conflicts of Interest

The author declares no conflicts of interest.

References

Khodabandelu, A.; Park, J. Agent-based modeling and simulation in construction. Autom. Constr. 2021, 131, 103882. [Google Scholar] [CrossRef]
An, L.; Grimm, V.; Sullivan, A.; Turner, B.; Malleson, N.; Heppenstall, A.; Vincenot, C.; Robinson, D.; Ye, X.; Liu, J.; et al. Challenges, tasks, and opportunities in modeling agent-based complex systems. Ecol. Model. 2021, 457, 109685. [Google Scholar] [CrossRef]
DeAngelis, D.L.; Diaz, S.G. Decision-Making in Agent-Based Modeling: A Current Review and Future Prospectus. Front. Ecol. Evol. 2019, 6, 237. [Google Scholar] [CrossRef]
Antosz, P.; Birks, D.; Edmonds, B.; Heppenstall, A.; Meyer, R.; Polhill, J.G.; O’Sullivan, D.; Wijermans, N. What do you want theory for?—A pragmatic analysis of the roles of “theory” in agent-based modelling. Environ. Model. Softw. 2023, 168, 105802. [Google Scholar] [CrossRef]
Zhang, W.; Liu, S.; Osgood, N.; Zhu, H.; Qian, Y.; Jia, P. Using simulation modelling and systems science to help contain COVID-19: A systematic review. Syst. Res. Behav. Sci. 2023, 40, 207–234. [Google Scholar] [CrossRef] [PubMed]
Wu, Z.; Peng, R.; Han, X.; Zheng, S.; Zhang, Y.; Xiao, C. Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations. arXiv 2023, arXiv:2311.06330. [Google Scholar]
Nazaryants, A.A. Agent-Based Modeling as the Basis for Sustainable Development of the Modern Economy. Ekon. Upr. Probl. Resheniya 2021, 2, 121–129. [Google Scholar] [CrossRef]
Gregorio, A.G.D. Neutron physics in the early 1930s. Hist. Stud. Phys. Biol. Sci. 2005, 35, 293–340. [Google Scholar] [CrossRef]
Santos, F.D. (Ed.) Science and Technology. From the Origins up to the Twenty-First Century. In Humans on Earth: From Origins to Possible Futures; The Frontiers Collection; Springer: Berlin/Heidelberg, Germany, 2012; pp. 1–39. ISBN 978-3-642-05360-3. [Google Scholar] [CrossRef]
González-Méndez, M.; Olaya, C.; Fasolino, I.; Grimaldi, M.; Obregón, N. Agent-Based Modeling for Urban Development Planning based on Human Needs. Conceptual Basis and Model Formulation. Land Use Policy 2021, 101, 105110. [Google Scholar] [CrossRef]
Raoufi, M.; Fayek, A.R. Fuzzy Monte Carlo Agent-Based Simulation of Construction Crew Performance. J. Constr. Eng. Manag. 2020, 146, 04020041. [Google Scholar] [CrossRef]
Jacobson, M.J.; Levin, J.A.; Kapur, M. Education as a Complex System: Conceptual and Methodological Implications. Educ. Res. 2019, 48, 112–119. [Google Scholar] [CrossRef]
Secchi, D.; Grimm, V.; Herath, D.B.; Homberg, F. Modeling and theorizing with agent-based sustainable development. Environ. Model. Softw. 2024, 171, 105891. [Google Scholar] [CrossRef]
Macal, C.M.; North, M.J. Tutorial on agent-based modelling and simulation. J. Simul. 2010, 4, 151–162. [Google Scholar] [CrossRef]
Outreach, R. Using Agent-Based Modelling to Understand Social Phenomena. Research Outreach. 2022. Available online: https://researchoutreach.org/articles/using-agent-based-modelling-understand-social-phenomena/ (accessed on 20 February 2024).
Agriesti, S.; Kuzmanovski, V.; Hollmén, J.; Roncoli, C.; Nahmias-Biran, B.-H. A Bayesian Optimization Approach for Calibrating Large-Scale Activity-Based Transport Models. IEEE Open J. Intell. Transp. Syst. 2023, 4, 740–754. [Google Scholar] [CrossRef]
Pleyer, J.; Fleck, C. Agent-based models in cellular systems. Front. Phys. 2023, 10, 968409. [Google Scholar] [CrossRef]
Chen, T.; Chen, Y.; Wang, X.; Wang, Y. Agent-based modeling in global pandemic propagation. In Proceedings of the 2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), Dalian, China, 14–16 April 2022; pp. 564–568. [Google Scholar] [CrossRef]
Guo, N.; Shi, C.; Yan, M.; Gao, X.; Wu, F. Modeling agricultural water-saving compensation policy: An ABM approach and application. J. Clean. Prod. 2022, 344, 131035. [Google Scholar] [CrossRef]
Zhang, W.; Valencia, A.; Chang, N.-B. Synergistic Integration Between Machine Learning and Agent-Based Modeling: A Multidisciplinary Review. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 2170–2190. [Google Scholar] [CrossRef]
Vodovotz, Y.; An, G. Agent-based models of inflammation in translational systems biology: A decade later. WIREs Syst. Biol. Med. 2019, 11, e1460. [Google Scholar] [CrossRef]
Decocq, G.; Regnault, P.; Lenoir, J.; Paccaut, F.; di Menza, L.; Delvoye, G.; Janvresse, E.; Closset-Kopp, D.; Goubet, O. Modelling plant community dynamics in changing forest ecosystems: A review. Bot. Lett. 2023, 170, 541–564. [Google Scholar] [CrossRef]
Moore, A.D. On the maximum growth equation used in forest gap simulation models. Ecol. Model. 1989, 45, 63–67. [Google Scholar] [CrossRef]
Validation of Jabowa: A Northeast Forest Simulator. Available online: https://kb.osu.edu/items/a2ec3b5d-25d1-5d61-ba0c-e34bdc2aa4d9 (accessed on 20 February 2024).
Bankes, S.; Lempert, R.; Popper, S. Making Computational Social Science Effective. Soc. Sci. Comput. Rev. 2002, 20, 377–388. [Google Scholar] [CrossRef]
Squazzoni, F. The Impact of Agent-Based Models in the Social Sciences after 15 Years of Incursions. Hist. Econ. Ideas 2010, 18, 197–234. [Google Scholar] [CrossRef]
Bonabeau, E. Agent-based modeling: Methods and techniques for simulating human systems. Proc. Natl. Acad. Sci. USA 2002, 99, 7280–7287. [Google Scholar] [CrossRef]
Moss, S.; Edmonds, B. Sociology and Simulation: Statistical and Qualitative Cross-Validation1. Am. J. Sociol. 2005, 110, 1095–1131. [Google Scholar] [CrossRef]
Uhrmacher, A.M.; Weyns, D. Multi-Agent Systems: Simulation and Applications; CRC Press: Boca Raton, FL, USA, 2009; ISBN 978-1-4200-7024-8. [Google Scholar]
Bruch, E.; Atwell, J. Agent-Based Models in Empirical Social Research. Sociol. Methods Res. 2015, 44, 186–221. [Google Scholar] [CrossRef]
Venkatramanan, S.; Lewis, B.; Chen, J.; Higdon, D.; Vullikanti, A.; Marathe, M. Using data-driven agent-based models for forecasting emerging infectious diseases. Epidemics 2017, 22, 43–49. [Google Scholar] [CrossRef] [PubMed]
Harik, G.; Alameddine, I.; Zurayk, R.; El-Fadel, M. An integrated socio-economic agent-based modeling framework towards assessing farmers’ decision making under water scarcity and varying utility functions. J. Environ. Manag. 2023, 329, 117055. [Google Scholar] [CrossRef]
Saghafi, Z.; Roshandel, R. Agent-based simulation for technology implementation in an energy-based industrial symbiosis network. Resour. Conserv. Recycl. Adv. 2024, 21, 200201. [Google Scholar] [CrossRef]
Huang, C.-Y. An Agent-Based Epidemic Simulation of Social Behaviors Affecting HIV Transmission among Taiwanese Homosexuals. Comput. Math. Methods Med. 2015, 2015, 867264. [Google Scholar] [CrossRef]
Chen, M.; DeHaven, M.; Kitschelt, I.; Lee, S.J.; Sicilian, M. Identifying Financial Crises Using Machine Learning on Textual Data. J. Risk Financ. Manag. 2023, 16, 161. [Google Scholar] [CrossRef]
Mls, K.; Kořínek, M.; Štekerová, K.; Tučník, P.; Bureš, V.; Čech, P.; Husáková, M.; Mikulecký, P.; Nacházel, T.; Ponce, D.; et al. Agent-based models of human response to natural hazards: Systematic review of tsunami evacuation. Nat. Hazards 2023, 115, 1887–1908. [Google Scholar] [CrossRef] [PubMed]
Arifovic, J.; Maschek, M. Currency crisis: Evolution of beliefs and policy experiments. J. Econ. Behav. Organ. 2012, 82, 131–150. [Google Scholar] [CrossRef]
Ionescu, Ș.; Delcea, C.; Chiriță, N.; Nica, I. Exploring the Use of Artificial Intelligence in Agent-Based Modeling Applications: A Bibliometric Study. Algorithms 2024, 17, 21. [Google Scholar] [CrossRef]
Dicks, M.; Paskaramoorthy, A.; Gebbie, T. A simple learning agent interacting with an agent-based market model. Phys. Stat. Mech. Its Appl. 2024, 633, 129363. [Google Scholar] [CrossRef]
Sharma, M.; Sehrawat, R. Decision-making in management of technology: A literature review. Int. J. Technol. Intell. Plan. 2021, 13, 38–62. [Google Scholar] [CrossRef]
Platas-López, A.; Guerra-Hernández, A.; Quiroz-Castellanos, M.; Cruz-Ramirez, N. A survey on agent-based modelling assisted by machine learning. Expert Syst. 2023, e13325. [Google Scholar] [CrossRef]
Huber, R.; Xiong, H.; Keller, K.; Finger, R. Bridging behavioural factors and standard bio-economic modelling in an agent-based modelling framework. J. Agric. Econ. 2022, 73, 35–63. [Google Scholar] [CrossRef]
Polhill, J.G.; Ge, J.; Hare, M.P.; Matthews, K.B.; Gimona, A.; Salt, D.; Yeluripati, J. Crossing the chasm: A ‘tube-map’ for agent-based social simulation of policy scenarios in spatially-distributed systems. GeoInformatica 2019, 23, 169–199. [Google Scholar] [CrossRef]
Datseris, G.; Vahdati, A.R.; DuBois, T.C. Agents.jl: A performant and feature-full agent based modelling software of minimal code complexity. Simulation 2022, 100, 1019–1031. [Google Scholar] [CrossRef]
Castro, J.; Drews, S.; Exadaktylos, F.; Foramitti, J.; Klein, F.; Konc, T.; Savin, I.; van den Bergh, J. A review of agent-based modeling of climate-energy policy. WIREs Clim. Chang. 2020, 11, e647. [Google Scholar] [CrossRef]
Zhang, B.; DeAngelis, D.L. An overview of agent-based models in plant biology and ecology. Ann. Bot. 2020, 126, 539–557. [Google Scholar] [CrossRef] [PubMed]
Blashaw, D.; Fukuda, M. An Interactive Environment to Support Agent-based Graph Programming. In Proceedings of the ICAART, Online, 3–5 February 2022; pp. 148–155. [Google Scholar] [CrossRef]
Lippe, M.; Bithell, M.; Gotts, N.; Natalini, D.; Barbrook-Johnson, P.; Giupponi, C.; Hallier, M.; Hofstede, G.; Page, C.; Matthews, R.; et al. Using agent-based modelling to simulate social-ecological systems across scales. GeoInformatica 2019, 23, 269–298. [Google Scholar] [CrossRef]
Uddin, M.J. How the agent-based banking model might facilitate financial inclusion and sustainability in Emerging Markets and Developing Economies (EMDEs) via economic circularity? Eur. J. Soc. Impact Circ. Econ. 2020, 1, 76–94. [Google Scholar] [CrossRef]
Breeze, P.R.; Squires, H.; Ennis, K.; Meier, P.; Hayes, K.; Lomax, N.; Shiell, A.; Kee, F.; de Vocht, F.; O’Flaherty, M.; et al. Guidance on the use of complex systems models for economic evaluations of public health interventions. Health Econ. 2023, 32, 1603–1625. [Google Scholar] [CrossRef]
Mazzetto, S. Multidisciplinary collaboration: An integrated and practical approach to the teaching of project management. Int. J. Contin. Eng. Educ. Life Long Learn. 2020, 30, 52–67. [Google Scholar] [CrossRef]
Nugroho, S.; Uehara, T. Systematic Review of Agent-Based and System Dynamics Models for Social-Ecological System Case Studies. Systems 2023, 11, 530. [Google Scholar] [CrossRef]
Mazzetto, S. Leadership and collaboration in project management education: A case study. In Resilient Structures and Sustainable Construction; ISEC Press: Fargo, ND, USA, 2017; pp. 1–6. [Google Scholar]
Romero, D.; Escudero, P. Adaptive Learning in Agent-Based Models: An Approach for Analyzing Human Behavior in Pandemic Crowding. Appl. Syst. Innov. 2023, 6, 113. [Google Scholar] [CrossRef]
Stieler, D.; Schwinn, T.; Leder, S.; Maierhofer, M.; Kannenberg, F.; Menges, A. Agent-based modeling and simulation in architecture. Autom. Constr. 2022, 141, 104426. [Google Scholar] [CrossRef]
Chandra, H.P.; Nugraha, P.; Putra, E.S. Building Information Modeling in the Architecture-engineering Construction Project in Surabaya. Procedia Eng. 2017, 171, 348–353. [Google Scholar] [CrossRef]
Nichols, A.C.; Phillips, S.; Soderlund, A.A. On Resilience-based Optimization of Closeproximity Multi-satellite Coordination via an Artificial Honeybee Colony Algorithm. In AIAA SCITECH 2023 Forum; American Institute of Aeronautics and Astronautics: Reston, VA, USA, 2023. [Google Scholar] [CrossRef]
Thneibat, M.; Thneibat, M.; Al-Shattarat, B.; Al-kroom, H. Development of an agent-based model to understand the diffusion of value management in construction projects as a sustainability tool. Alex. Eng. J. 2022, 61, 747–761. [Google Scholar] [CrossRef]
Wijermans, N.; Scholz, G.; Chappin, É.; Heppenstall, A.; Filatova, T.; Polhill, J.G.; Semeniuk, C.; Stöppler, F. Agent decision-making: The Elephant in the Room—Enabling the justification of decision model fit in social-ecological models. Environ. Model. Softw. 2023, 170, 105850. [Google Scholar] [CrossRef]
Castiglione, F. Agent-Based Modeling and Simulation, Introduction to. In Complex Social and Behavioral Systems: Game Theory and Agent-Based Models; Sotomayor, M., Pérez-Castrillo, D., Castiglione, F., Eds.; Encyclopedia of Complexity and Systems Science Series; Springer: New York, NY, USA, 2020; pp. 661–665. ISBN 978-1-07-160368-0. [Google Scholar] [CrossRef]
Jeong, S.; Elliott, J.B.; Feng, Z.; Feldon, D.F. Understanding Complex Ecosystems Through an Agent-Based Participatory Watershed Simulation. J. Sci. Educ. Technol. 2022, 31, 691–705. [Google Scholar] [CrossRef]
Mazzetto, S. A practical, multidisciplinary approach for assessing leadership in project management education. J. Appl. Res. High. Educ. 2019, 11, 50–65. [Google Scholar] [CrossRef]
Eskandar, Y.; Hosny, S.S.; Abdelmohsen, S.; Hamza, H. Utilizing Artificial Intelligence Techniques in Complex Form Generation. Eng. Res. J. Shoubra 2024, 53, 34–39. [Google Scholar] [CrossRef]
Lindkvist, E.; Wijermans, N.; Daw, T.M.; Gonzalez-Mon, B.; Giron-Nava, A.; Johnson, A.F.; van Putten, I.; Basurto, X.; Schlüter, M. Navigating Complexities: Agent-Based Modeling to Support Research, Governance, and Management in Small-Scale Fisheries. Front. Mar. Sci. 2020, 6, 733. [Google Scholar] [CrossRef]
Bian, J.; Huang, Y.; Dai, H.; Xu, J.; Wei, R.; Sun, L.; Guo, Y.; Guo, J. Evolution of digital twins in precision health applications: A scoping review study. 2024; preprint. [Google Scholar] [CrossRef]
Qiu, H.; Chen, Y.; Zhang, H.; Yi, W.; Li, Y. Evolutionary digital twin model with an agent-based discrete-event simulation method. Appl. Intell. 2023, 53, 6178–6194. [Google Scholar] [CrossRef]
Rainey, L.B.; Tolk, A. Modeling and Simulation Support for System of Systems Engineering Applications; Wiley: Hoboken, NJ, USA, 2015. [Google Scholar]
Savaglio, C.; Ganzha, M.; Paprzycki, M.; Bădică, C.; Ivanović, M.; Fortino, G. Agent-based Internet of Things: State-of-the-art and research challenges. Future Gener. Comput. Syst. 2020, 102, 1038–1053. [Google Scholar] [CrossRef]
Abdelalim, A.M.; Said, S.O.; Alnaser, A.A.; Sharaf, A.; ElSamadony, A.; Kontoni, D.-P.N.; Tantawy, M. Agent-Based Modeling for Construction Resource Positioning Using Digital Twin and BLE Technologies. Buildings 2024, 14, 1788. [Google Scholar] [CrossRef]
Galuzin, V.; Galitskaya, A.; Grachev, S.; Larukhin, V.; Novichkov, D.; Skobelev, P.; Zhilyaev, A. Autonomous digital twin of enterprise: Method and toolset for knowledge-based multi-agent adaptive management of tasks and resources in real time. Mathematics 2022, 10, 1662. [Google Scholar] [CrossRef]
Orozco-Romero, A.; Arias-Portela, C.Y.; Saucedo, J.A.M. The use of agent-based models boosted by digital twins in the supply chain: A literature review. In Intelligent Computing and Optimization: Proceedings of the 2nd International Conference on Intelligent Computing and Optimization 2019 (ICO 2019), Koh Samui, Thailand, 3–9 October 2019; Springer: Berlin/Heidelberg, Germany, 2020; pp. 642–652. [Google Scholar]
Ambra, T.; Macharis, C. Agent-based digital twins (ABM-DT) in synchromodal transport and logistics: The fusion of virtual and pysical spaces. In Proceedings of the 2020 Winter Simulation Conference (WSC), Orlando, FL, USA, 14–18 December 2020; IEEE: Piscataway, NJ, USA, 2020; pp. 159–169. [Google Scholar]
Yi, H. Visualized Co-Simulation of Adaptive Human Behavior and Dynamic Building Performance: An Agent-Based Model (ABM) and Artificial Intelligence (AI) Approach for Smart Architectural Design. Sustainability 2020, 12, 6672. [Google Scholar] [CrossRef]
Su, B.; Wang, S. An agent-based distributed real-time optimal control strategy for building HVAC systems for applications in the context of future IoT-based smart sensor networks. Appl. Energy 2020, 274, 115322. [Google Scholar] [CrossRef]
Mykoniatis, K.; Harris, G.A. A digital twin emulator of a modular production system using a data-driven hybrid modeling and simulation approach. J. Intell. Manuf. 2021, 32, 1899–1911. [Google Scholar] [CrossRef]
Huang, J.; Cui, Y.; Zhang, L.; Tong, W.; Shi, Y.; Liu, Z. An Overview of Agent-Based Models for Transport Simulation and Analysis. J. Adv. Transp. 2022, 2022, e1252534. [Google Scholar] [CrossRef]
Clemen, T.; Ahmady-Moghaddam, N.; Lenfers, U.A.; Ocker, F.; Osterholz, D.; Ströbele, J.; Glake, D. Multi-Agent Systems and Digital Twins for Smarter Cities. In Proceedings of the 2021 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, Suffolk, VA, USA, 31 May–2 June 2021; Association for Computing Machinery: New York, NY, USA, 2021; pp. 45–55. [Google Scholar] [CrossRef]
Wang, H.; Chen, X.; Jia, F.; Cheng, X. Digital twin-supported smart city: Status, challenges and future research directions. Expert Syst. Appl. 2023, 217, 119531. [Google Scholar] [CrossRef]
Lu, Y.; Liu, C.; Kevin, I.; Wang, K.; Huang, H.; Xu, X. Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues. Robot. Comput. Integr. Manuf. 2020, 61, 101837. [Google Scholar] [CrossRef]
Eugeni, F.; Sacco, S.; Di Ludovico, D. Urban Safety and Resilience: Agent-Based Modelling Simulations for Pre-disaster Planning. In International Conference on Innovation in Urban and Regional Planning; Springer: Berlin/Heidelberg, Germany, 2023; pp. 563–572. [Google Scholar]
Groenewolt, A.; Schwinn, T.; Nguyen, L.; Menges, A. An interactive agent-based framework for materialization-informed architectural design. Swarm Intell. 2018, 12, 155–186. [Google Scholar] [CrossRef]
Leder, S.; Menges, A. Introducing Agent-Based Modeling Methods for Designing Architectural Structures with Multiple Mobile Robotic Systems. In Towards Radical Regeneration; Gengnagel, C., Baverel, O., Betti, G., Popescu, M., Thomsen, M.R., Wurm, J., Eds.; Springer International Publishing: Cham, Switzerland; Berlin, Germany, 2023; pp. 71–83. [Google Scholar]
Scheutz, M.; Mayer, T. Combining agent-based modeling with big data methods to support architectural and urban design. In Understanding Complex Urban Systems: Integrating Multidisciplinary Data in Urban Models; Springer: Berlin/Heidelberg, Germany, 2016; pp. 15–31. [Google Scholar]
Liang, X.; Shen, G.Q.; Bu, S. Multiagent Systems in Construction: A Ten-Year Review. J. Comput. Civ. Eng. 2016, 30, 04016016. [Google Scholar] [CrossRef]
Moscatelli, M. Rethinking the Heritage through a Modern and Contemporary Reinterpretation of Traditional Najd Architecture, Cultural Continuity in Riyadh. Buildings 2023, 13, 1471. [Google Scholar] [CrossRef]
Sirror, H.; Labib, W.; Abowardah, E.; Metwally, W.; Mitchell, C. Sustainability in the Workplace: Evaluating Indoor Environmental Quality of a Higher Education Building in Riyadh. Buildings 2024, 14, 2115. [Google Scholar] [CrossRef]
Azouqah, H.; Alomar, N.; Kaadan, L.; Sonbul, M.; Abdulaziz, H.; Labib, W. Sustainable Local Materials: A Study of Adobe Bricks in Saudi Arabia. Mater. Sci. Forum 2021, 1047, 163–173. [Google Scholar] [CrossRef]
Moussa, R.A. A Responsive Approach for Designing Shared Urban Spaces in Tourist Villages. Sustainability 2023, 15, 7549. [Google Scholar] [CrossRef]
Dwidar, S.; Sirror, H.; Derbali, A.; Abdelgawad, D.; Abdelsattar, A. Importance if internal courtyards in designing historical and contemporary Masjid. J. Islam. Archit. 2022, 7, 356. [Google Scholar] [CrossRef]
Rajabi, M.; Radzi, A.; Rezaeiashtiani, M.; Famili, A.; Rashidi, M.; Rahman, R. Key assessment criteria for organizational BIM capabilities: A cross-regional study. Buildings 2022, 12, 1013. [Google Scholar] [CrossRef]
Rajabi, M.S.; Rezaeiashtiani, M.; Radzi, A.R.; Famili, A.; Rezaeiashtiani, A.; Rahman, R.A. Underlying factors and strategies for organizational BIM capabilities: The case of Iran. Appl. Syst. Innov. 2022, 5, 109. [Google Scholar] [CrossRef]
Santos, R.; Costa, A.A.; Silvestre, J.D.; Pyl, L. Informetric analysis and review of literature on the role of BIM in sustainable construction. Autom. Constr. 2019, 103, 221–234. [Google Scholar] [CrossRef]
Working with JSON—Learn Web Development|MDN. Available online: https://developer.mozilla.org/en-US/docs/Learn/JavaScript/Objects/JSON (accessed on 25 February 2024).
Python.Org. Welcome to Python.org. Available online: https://www.python.org/ (accessed on 25 February 2024).
Ganji, M. Distribution-Based Sub-Population Selection (DSPS): A Method for in-Silico Reproduction of Clinical Trials Outcomes. arXiv 2024, arXiv:240900232. [Google Scholar]
Koseoglu, O.; Nurtan-Gunes, E.T. Mobile BIM implementation and lean interaction on construction site: A case study of a complex airport project. Eng. Constr. Archit. Manag. 2018, 25, 1298–1321. [Google Scholar] [CrossRef]
Garcés, G.; Peña, C. A Review on Lean Construction for Construction Project Management: Una revisión sobre Lean Construction para la Gestión de Proyectos de Construcción. Rev. Ing. Constr. 2023, 38, 43–60. [Google Scholar] [CrossRef]
Mellado, F.; Lou, E.C.W. Building information modelling, lean and sustainability: An integration framework to promote performance improvements in the construction industry. Sustain. Cities Soc. 2020, 61, 102355. [Google Scholar] [CrossRef]
Rizo-Maestre, C.; González-Avilés, Á.; Galiano-Garrigós, A.; Andújar-Montoya, M.D.; Puchol-García, J.A. UAV + BIM: Incorporation of Photogrammetric Techniques in Architectural Projects with Building Information Modeling Versus Classical Work Processes. Remote Sens. 2020, 12, 2329. [Google Scholar] [CrossRef]
Uvarova, S.S.; Belyaeva, S.V.; Orlov, A.K.; Kankhva, V.S. Cost Forecasting for Building Materials under Conditions of Uncertainty: Methodology and Practice. Buildings 2023, 13, 2371. [Google Scholar] [CrossRef]
Aslam, M.; Gao, Z.; Smith, G. Exploring factors for implementing lean construction for rapid initial successes in construction. J. Clean. Prod. 2020, 277, 123295. [Google Scholar] [CrossRef]
Saieg, P.; Sotelino, E.D.; Nascimento, D.; Caiado, R.G.G. Interactions of Building Information Modeling, Lean and Sustainability on the Architectural, Engineering and Construction industry: A systematic review. J. Clean. Prod. 2018, 174, 788–806. [Google Scholar] [CrossRef]
Ramírez-Fráncel, L.A.; García-Herrera, L.V.; Losada-Prado, S.; Reinoso-Flórez, G.; Sánchez-Hernández, A.; Estrada-Villegas, S.; Lim, B.K.; Guevara, G. Bats and their vital ecosystem services: A global review. Integr. Zool. 2022, 17, 2–23. [Google Scholar] [CrossRef]
Sbiti, M.; Beddiar, K.; Beladjine, D.; Perrault, R.; Mazari, B. Toward BIM and LPS Data Integration for Lean Site Project Management: A State-of-the-Art Review and Recommendations. Buildings 2021, 11, 196. [Google Scholar] [CrossRef]
Madusha, M.D.Y.; Francis, M.; Liyanawatta, T.N. Applicability of Bim Technology for Enhancing the Lean Construction Process in Sri Lanka. 2023. Available online: http://dl.lib.uom.lk/handle/123/21266 (accessed on 3 March 2024).
Ding, Z.; Wang, X.; Sanjayan, J.; Zou, P.X.W.; Ding, Z.-K. A Feasibility Study on HPMC-Improved Sulphoaluminate Cement for 3D Printing. Materials 2018, 11, 2415. [Google Scholar] [CrossRef]
Alizadehsalehi, S.; Hadavi, A.; Huang, J.C. Virtual Reality for Design and Construction Education Environment. In Proceedings of the AEI 2019, Tysons, VA, USA, 3–6 April 2019; pp. 193–203. [Google Scholar] [CrossRef]
Cairampoma-Caro, K.; Vargas-Florez, J.; Romero-Izaga, C. Towards a Lean Construction toolbox to improve social projects management. Braz. J. Oper. Prod. Manag. 2022, 19, 1–13. [Google Scholar] [CrossRef]
Besklubova, S.; Zhang, X. Improving Construction Productivity by Integrating the Lean Concept and the Clancey Heuristic Model. Sustainability 2019, 11, 4535. [Google Scholar] [CrossRef]
Erusta, N.E.; Sertyesilisik, B. An Investigation into Improving Occupational Health and Safety Performance of Construction Projects Through Usage of BIM for Lean Management. In Advances in Building Information Modeling; Ofluoglu, S., Ozener, O.O., Isikdag, U., Eds.; Springer International Publishing: Cham, Switzerland; Berlin, Germany, 2020; pp. 91–100. [Google Scholar]
Fang, Q.; Chen, X.; Castro-Lacouture, D.; Li, C. Intervention and management of construction workers’ unsafe behavior: A simulation digital twin model. Adv. Eng. Inform. 2023, 58, 102182. [Google Scholar] [CrossRef]
Korb, S.; Sacks, R. Towards Multi-Project Simulation of a Lean Production System for Customized Apartment Buildings. In Proceedings of the 2018 Winter Simulation Conference (WSC), Gothenburg, Sweden, 9–12 December 2018; pp. 3897–3908. [Google Scholar] [CrossRef]
Oktavia Mulyono, Y.; Sukhbaatar, U.; Cabrera, D. ‘Hard’ and ‘Soft’ Methods in Complex Adaptive Systems (CAS): Agent Based Modeling (ABM) and the Agent Based Approach (ABA). J. Syst. Think. 2023, 3, 1–33. [Google Scholar] [CrossRef]
Heydari, B.; Pennock, M.J. Guiding the behavior of sociotechnical systems: The role of agent-based modeling. Syst. Eng. 2018, 21, 210–226. [Google Scholar] [CrossRef]
Harris, D.; Da Silva, F.L.; Su, W.; Glatt, R. A Review on Simulation Platforms for Agent-Based Modeling in Electrified Transportation. IEEE Trans. Intell. Transp. Syst. 2024, 25, 1131–1147. [Google Scholar] [CrossRef]
Uthpala, N.; Hansika, N.; Dissanayaka, S.; Tennakoon, K.; Dharmarathne, S.; Vidanarachchi, R.; Alawatugoda, J.; Herath, D. Analyzing transportation mode interactions using agent-based models. SN Appl. Sci. 2023, 5, 357. [Google Scholar] [CrossRef]
Price, R.B.; Woody, M.L.; Panny, B.; Siegle, G.J. Pinpointing Mechanisms of a Mechanistic Treatment: Dissociable Roles for Overt and Covert Attentional Processes in Acute and Long-Term Outcomes Following Attention-Bias Modification. Clin. Psychol. Sci. 2019, 7, 1042–1062. [Google Scholar] [CrossRef]
Assaf, M.; Assaf, S.; Correa, W.; Lemouchi, R.; Mohamed, Y. A Hybrid Simulation-Based Optimization Framework for Managing Modular Bridge Construction Projects: A Cable-Stayed Bridge Case Study. In Proceedings of the 2023 Winter Simulation Conference (WSC), San Antonio, TX, USA, 10–13 December 2023; pp. 3094–3105. [Google Scholar] [CrossRef]
Sakas, D.P.; Giannakopoulos, N.T.; Terzi, M.C.; Kanellos, N.; Liontakis, A. Digital Transformation Management of Supply Chain Firms Based on Big Data from DeFi Social Media Profiles. Electronics 2023, 12, 4219. [Google Scholar] [CrossRef]
Li, W.; Yuan, J.; Zhang, G.; Wei, S.; Zhang, B.; Skibniewski, M.J. Agent-Based Simulation Modeling for the Evaluation and Dynamic Adjustment of Project Benefits in Urban Rail Transit PPPs. J. Manag. Eng. 2023, 39, 04022074. [Google Scholar] [CrossRef]
Müller, B.; Hoffmann, F.; Heckelei, T.; Müller, C.; Hertel, T.W.; Polhill, J.G.; van Wijk, M.; Achterbosch, T.; Alexander, P.; Brown, C.; et al. Modelling food security: Bridging the gap between the micro and the macro scale. Glob. Environ. Chang. 2020, 63, 102085. [Google Scholar] [CrossRef]
Khansari, N.; Hewitt, E. Incorporating an agent-based decision tool to better understand occupant pathways to GHG reductions in NYC buildings. Cities 2020, 97, 102503. [Google Scholar] [CrossRef]
Rouzafzoon, J. Development of Transportation and Supply Chain Problems with the Combination of Agent-Based Simulation and Network Optimization. Ph.D. Thesis, Vaasan Yliopisto, Vaasa, Finland, 2023. Available online: https://osuva.uwasa.fi/handle/10024/15296 (accessed on 1 March 2024).
Aoujil, Z.; Hanine, M. Aoujil, Z.; Hanine, M. A Review on Artificial Intelligence and Behavioral Macroeconomics. In Innovations in Smart Cities Applications; Ben Ahmed, M., Boudhir, A.A., El Meouche, R., Karaș, İ.R., Eds.; Springer Nature Switzerland: Cham, Switzerland; Berlin, Germany, 2024; Volume 7, pp. 332–341. [Google Scholar]
Wei, Y.; Lei, Z.; Altaf, M.S. Simulation-based comparison of push- and pull-based planning in panelized construction. Autom. Constr. 2024, 158, 105228. [Google Scholar] [CrossRef]
Collins, A.J.; Sabz Ali Pour, F.; Jordan, C.A. Past challenges and the future of discrete event simulation. J. Def. Model. Simul. 2023, 20, 351–369. [Google Scholar] [CrossRef]
Ding, Z.; Gong, W.; Li, S.; Wu, Z. System Dynamics versus Agent-Based Modeling: A Review of Complexity Simulation in Construction Waste Management. Sustainability 2018, 10, 2484. [Google Scholar] [CrossRef]
Rodrigues, F.; Baptista, J.S.; Pinto, D. BIM Approach in Construction Safety—A Case Study on Preventing Falls from Height. Buildings 2022, 12, 73. [Google Scholar] [CrossRef]
Reyes Aguilera, P.; Trujillo Rufino, M.T. 3D Virtual Space for Collaborative Design Reviews. 2023. Available online: https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-23228 (accessed on 3 March 2024).
Alhussein, H.; Shehab, L.; Hamzeh, F. Improvisation in Construction Planning: An Agent-Based Simulation Approach. Buildings 2022, 12, 1608. [Google Scholar] [CrossRef]
Yao, R.; Hu, Y.; Varga, L. Applications of Agent-Based Methods in Multi-Energy Systems—A Systematic Literature Review. Energies 2023, 16, 2456. [Google Scholar] [CrossRef]
Son, J.; Rojas, E.M.; Shin, S.-W. Application of agent-based modeling and simulation to understanding complex management problems in CEM research. J. Civ. Eng. Manag. 2015, 21, 998–1013. [Google Scholar] [CrossRef]
Ghimire, P.; Kim, K.; Acharya, M. Generative AI in the Construction Industry: Opportunities & Challenges. Buildings 2024, 14, 220. [Google Scholar] [CrossRef]
Merow, C.; Smith, M.J.; Edwards, T.C., Jr.; Guisan, A.; McMahon, S.M.; Normand, S.; Thuiller, W.; Wüest, R.O.; Zimmermann, N.E.; Elith, J. What do we gain from simplicity versus complexity in species distribution models? Ecography 2014, 37, 1267–1281. [Google Scholar] [CrossRef]
North, M.J.; Macal, C.M.; Aubin, J.S.; Thimmapuram, P.; Bragen, M.; Hahn, J.; Karr, J.; Brigham, N.; Lacy, M.E.; Hampton, D. Multiscale agent-based consumer market modeling. Complexity 2010, 15, 37–47. [Google Scholar] [CrossRef]
Morgan, N.A.; Jayachandran, S.; Hulland, J.; Kumar, B.; Katsikeas, C.; Somosi, A. Marketing performance assessment and accountability: Process and outcomes. Int. J. Res. Mark. 2022, 39, 462–481. [Google Scholar] [CrossRef]
Tarafdar, P.; Leung, A.C.M.; Yue, W.T.; Bose, I. Understanding the impact of augmented reality product presentation on diagnosticity, cognitive load, and product sales. Int. J. Inf. Manag. 2024, 75, 102744. [Google Scholar] [CrossRef]
Tian, Z.; Qiu, L.; Wang, L. Drivers and influencers of blockchain and cloud-based business sustainability accounting in China: Enhancing practices and promoting adoption. PLoS ONE 2024, 19, e0295802. [Google Scholar] [CrossRef]
Silverman, E.; Gostoli, U.; Picascia, S.; Almagor, J.; McCann, M.; Shaw, R.; Angione, C. Situating agent-based modelling in population health research. Emerg. Themes Epidemiol. 2021, 18, 10. [Google Scholar] [CrossRef] [PubMed]
Akhatova, A.; Kranzl, L.; Schipfer, F.; Heendeniya, C.B. Agent-Based Modelling of Urban District Energy System Decarbonisation—A Systematic Literature Review. Energies 2022, 15, 554. [Google Scholar] [CrossRef]
Kim, J.; Conte, M.; Oh, Y.; Park, J. From Barter to Market: An Agent-Based Model of Prehistoric Market Development. J. Archaeol. Method Theory 2024, 31, 1232–1271. [Google Scholar] [CrossRef]
Sturley, C.; Newing, A.; Heppenstall, A. Evaluating the potential of agent-based modelling to capture consumer grocery retail store choice behaviours. Int. Rev. Retail Distrib. Consum. Res. 2018, 28, 27–46. [Google Scholar] [CrossRef]
Twomey, P.; Cadman, R. Agent-based modelling of customer behaviour in the telecoms and media markets. info 2002, 4, 56–63. [Google Scholar] [CrossRef]
van der Veen, R.A.C.; Kisjes, K.H.; Nikolic, I. Exploring policy impacts for servicising in product-based markets: A generic agent-based model. J. Clean. Prod. 2017, 145, 1–13. [Google Scholar] [CrossRef]
Chica, M.; Cordón, O.; Robles, J.F.; Garrido, A.; Mingot, J.; Damas, S. Zio: An artificial intelligence digital twin to build virtual markets. In Proceedings of the 2023 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA, 5–6 June 2023; pp. 173–174. Available online: https://ieeexplore.ieee.org/abstract/document/10195144?casa_token=Sc6Lfh3a5p0AAAAA:4zznMT23PGu2OkZOcS5IDAJ_YYcX65ws_wO-5Nt8qUZ6xzuRvUN4JXKaISx2EDTbo_TNV08eTP8 (accessed on 3 March 2024).
Fan, R.; Yao, Q.; Chen, R.; Qian, R. Agent-based simulation model of panic buying behavior in urban public crisis events: A social network perspective. Sustain. Cities Soc. 2024, 100, 105002. [Google Scholar] [CrossRef]
Tan, Y.; Lu, Y. Why Excavation of a Small Air Shaft Caused Excessively Large Displacements: Forensic Investigation. J. Perform. Constr. Facil. 2017, 31, 04016083. [Google Scholar] [CrossRef]
Haas, M.; Mongeard, L.; Ulrici, L.; D’Aloïa, L.; Cherrey, A.; Galler, R.; Benedikt, M. Applicability of excavated rock material: A European technical review implying opportunities for future tunnelling projects. J. Clean. Prod. 2021, 315, 128049. [Google Scholar] [CrossRef]
Rabbat, C.; Awad, S.; Villot, A.; Rollet, D.; Andrès, Y. Sustainability of biomass-based insulation materials in buildings: Current status in France, end-of-life projections and energy recovery potentials. Renew. Sustain. Energy Rev. 2022, 156, 111962. [Google Scholar] [CrossRef]
Ma, M.; Tam, V.W.Y.; Le, K.N.; Li, W. Challenges in current construction and demolition waste recycling: A China study. Waste Manag. 2020, 118, 610–625. [Google Scholar] [CrossRef]
Bozdoğan, A.; Görkemli Aykut, L.; Demirel, N. An agent-based modeling framework for the design of a dynamic closed-loop supply chain network. Complex Intell. Syst. 2023, 9, 247–265. [Google Scholar] [CrossRef] [PubMed]
Zhu, C.; Zhang, J.; Taheri, A.; Zhou, N.; Li, Z.; Li, M. Control effect of coal mining solid-waste backfill for ground surface movement in slice mining: A case study of the Nantun Coal Mine. Environ. Sci. Pollut. Res. 2023, 30, 27270–27288. [Google Scholar] [CrossRef]
Mabey, C.S.; Salmon, J.L.; Mattson, C.A. Agent-Based Product-Social-Impact-Modeling: A Systematic Literature Review and Modeling Process. J. Mech. Des. 2023, 145, 110801. [Google Scholar] [CrossRef]
Li, Y.L.; Tsang, Y.P.; Wu, C.H.; Lee, C.K.M. A multi-agent digital twin–enabled decision support system for sustainable and resilient supplier management. Comput. Ind. Eng. 2024, 187, 109838. [Google Scholar] [CrossRef]
Pour Rahimian, F.; Seyedzadeh, S.; Oliver, S.; Rodriguez, S.; Dawood, N. On-demand monitoring of construction projects through a game-like hybrid application of BIM and machine learning. Autom. Constr. 2020, 110, 103012. [Google Scholar] [CrossRef]
Guo, B.H.W.; Yiu, T.W.; González, V.A. Identifying behaviour patterns of construction safety using system archetypes. Accid. Anal. Prev. 2015, 80, 125–141. [Google Scholar] [CrossRef]
Spieler, E.A. (Re)Assessing the Grand Bargain: Compensation for Work Injuries in the United States, 1900–2017. Rutgers Univ. Law Rev. 2016, 69, 891. [Google Scholar]
Umar, T.; Wamuziri, S.C. A Review of Construction Safety, Challenges and Opportunities—Oman Perspective. 2016. Available online: http://dl.lib.uom.lk/handle/123/17294 (accessed on 3 March 2024).
Tong, R.; Li, H.; Zhang, B.; Yang, X.; Ma, X. Modeling of unsafe behavior risk assessment: A case study of Chinese furniture manufacturers. Saf. Sci. 2021, 136, 105157. [Google Scholar] [CrossRef]
Mohammadi, A.; Tavakolan, M. Identifying safety archetypes of construction workers using system dynamics and content analysis. Saf. Sci. 2020, 129, 104831. [Google Scholar] [CrossRef]
Mohammadi, A.; Tavakolan, M.; Khosravi, Y. Factors influencing safety performance on construction projects: A review. Saf. Sci. 2018, 109, 382–397. [Google Scholar] [CrossRef]
Mohammadfam, I.; Ghasemi, F.; Kalatpour, O.; Moghimbeigi, A. Constructing a Bayesian network model for improving safety behavior of employees at workplaces. Appl. Ergon. 2017, 58, 35–47. [Google Scholar] [CrossRef] [PubMed]
Yuan, R.; Guo, F.; Qian, Y.; Cheng, B.; Li, J.; Tang, X.; Peng, X. A system dynamic model for simulating the potential of prefabrication on construction waste reduction. Environ. Sci. Pollut. Res. 2022, 29, 12589–12600. [Google Scholar] [CrossRef]
Mitropoulos, P.; Memarian, B. Team Processes and Safety of Workers: Cognitive, Affective, and Behavioral Processes of Construction Crews. J. Constr. Eng. Manag. 2012, 138, 1181–1191. [Google Scholar] [CrossRef]
Wang, H.-H.; Chen, J.-H.; Arifai, A.M.; Gheisari, M. Exploring Empirical Rules for Construction Accident Prevention Based on Unsafe Behaviors. Sustainability 2022, 14, 4058. [Google Scholar] [CrossRef]
Liu, W.; Meng, Q.; Li, Z.; Hu, X. Applications of Computer Vision in Monitoring the Unsafe Behavior of Construction Workers: Current Status and Challenges. Buildings 2021, 11, 409. [Google Scholar] [CrossRef]
He, C.; McCabe, B.; Jia, G.; Sun, J. Effects of Safety Climate and Safety Behavior on Safety Outcomes between Supervisors and Construction Workers. J. Constr. Eng. Manag. 2020, 146, 04019092. [Google Scholar] [CrossRef]
Man, S.S.; Chan, A.H.S.; Alabdulkarim, S.; Zhang, T. The effect of personal and organizational factors on the risk-taking behavior of Hong Kong construction workers. Saf. Sci. 2021, 136, 105155. [Google Scholar] [CrossRef]
Khoshnava, S.M.; Rostami, R.; Zin, R.M.; Mishra, A.R.; Rani, P.; Mardani, A.; Alrasheedi, M. Assessing the impact of construction industry stakeholders on workers’ unsafe behaviours using extended decision making approach. Autom. Constr. 2020, 118, 103162. [Google Scholar] [CrossRef]
Kessler, S.R.; Lucianetti, L.; Pindek, S.; Spector, P.E. “Walking the talk”: The role of frontline supervisors in preventing workplace accidents. Eur. J. Work Organ. Psychol. 2020, 29, 450–461. [Google Scholar] [CrossRef]
Hasle, P.; Uhrenholdt Madsen, C.; Hansen, D. Integrating operations management and occupational health and safety: A necessary part of safety science! Saf. Sci. 2021, 139, 105247. [Google Scholar] [CrossRef]
Read, G.J.M.; Salmon, P.M.; Thompson, J.; McClure, R.J. Simulating the behaviour of complex systems: Computational modelling in ergonomics. Ergonomics 2020, 63, 931–937. [Google Scholar] [CrossRef]
Holman, M.; Walker, G.; Lansdown, T.; Hulme, A. Radical systems thinking and the future role of computational modelling in ergonomics: An exploration of agent-based modelling. Ergonomics 2020, 63, 1057–1074. [Google Scholar] [CrossRef]
Maïzi, Y.; Bendavid, Y. Hybrid RFID-IoT simulation modeling approach for analyzing scrubs’ distribution solutions in operating rooms. Bus. Process Manag. J. 2023, 29, 1734–1761. [Google Scholar] [CrossRef]
Gurram, S.; Sivaraman, V.; Apple, J.T.; Pinjari, A.R. Agent-based modeling to simulate road travel using Big Data from smartphone GPS: An application to the continental United States. In Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, 9–12 December 2019; pp. 3553–3562. [Google Scholar] [CrossRef]
Huang, X.; Zhang, C.; Ye, Y.; Jiang, H. Construction site integrated monitoring system based on fusion of visual localization and UWB. In Proceedings of the Second International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2023), Nanjing, China, 26–28 May 2023; SPIE: Bellingham, DC, USA, 2023; Volume 12744, pp. 250–256. [Google Scholar] [CrossRef]
Yang, G.; Sun, D. Intelligent safety production monitoring system based on UWB. In Proceedings of the International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023), Nanchang, China, 17–19 March 2023; SPIE: Bellingham, DC, USA, 2023; Volume 12700, pp. 764–770. [Google Scholar] [CrossRef]
Morteza, A.; Ilbeigi, M.; Schwed, J. A blockchain information management framework for construction safety. In Proceedings of the Computing in Civil Engineering 2021, Orlando, FL, USA, 12–14 September 2021; pp. 342–349. [Google Scholar]
Berger, C.; Mahdavi, A. Review of current trends in agent-based modeling of building occupants for energy and indoor-environmental performance analysis. Build. Environ. 2020, 173, 106726. [Google Scholar] [CrossRef]
Malik, J.; Mahdavi, A.; Azar, E.; Chandra Putra, H.; Berger, C.; Andrews, C.; Hong, T. Ten questions concerning agent-based modeling of occupant behavior for energy and environmental performance of buildings. Build. Environ. 2022, 217, 109016. [Google Scholar] [CrossRef]
Lee, S. Development of Self-Tuned Indoor Thermal Environments. Ph.D. Thesis, Purdue University Graduate School, West Lafayette, IN, USA, 2019. Available online: https://hammer.purdue.edu/articles/thesis/DEVELOPMENT_OF_SELF-TUNED_INDOOR_THERMAL_ENVIRONMENTS/11309093/1 (accessed on 3 March 2024).
Wong, J.K.W.; Bameri, F.; Ahmadian Fard Fini, A.; Maghrebi, M. Tracking indoor construction progress by deep-learning-based analysis of site surveillance video. Constr. Innov. 2023; ahead-of-print. [Google Scholar] [CrossRef]
Hosamo, H.H.; Nielsen, H.K.; Kraniotis, D.; Svennevig, P.R.; Svidt, K. Improving building occupant comfort through a digital twin approach: A Bayesian network model and predictive maintenance method. Energy Build. 2023, 288, 112992. [Google Scholar] [CrossRef]
Hosamo, H.H.; Nielsen, H.K.; Kraniotis, D.; Svennevig, P.R.; Svidt, K. Digital Twin framework for automated fault source detection and prediction for comfort performance evaluation of existing non-residential Norwegian buildings. Energy Build. 2023, 281, 112732. [Google Scholar] [CrossRef]
Hosamo, H.H.; Tingstveit, M.S.; Nielsen, H.K.; Svennevig, P.R.; Svidt, K. Multiobjective optimization of building energy consumption and thermal comfort based on integrated BIM framework with machine learning-NSGA II. Energy Build. 2022, 277, 112479. [Google Scholar] [CrossRef]
Hosamo, H.H.; Nielsen, H.K.; Alnmr, A.N.; Svennevig, P.R.; Svidt, K. A review of the Digital Twin technology for fault detection in buildings. Front. Built Environ. 2022, 8, 1013196. [Google Scholar] [CrossRef]
Chiacchio, F.; Pennisi, M.; Russo, G.; Motta, S.; Pappalardo, F. Agent-Based Modeling of the Immune System: NetLogo, a Promising Framework. BioMed Res. Int. 2014, 2014, 907171. [Google Scholar] [CrossRef] [PubMed]
Muravev, D.; Hu, H.; Rakhmangulov, A.; Mishkurov, P. Multi-agent optimization of the intermodal terminal main parameters by using AnyLogic simulation platform: Case study on the Ningbo-Zhoushan Port. Int. J. Inf. Manag. 2021, 57, 102133. [Google Scholar] [CrossRef]
Jia, M.; Srinivasan, R.S.; Raheem, A.A. From occupancy to occupant behavior: An analytical survey of data acquisition technologies, modeling methodologies and simulation coupling mechanisms for building energy efficiency. Renew. Sustain. Energy Rev. 2017, 68, 525–540. [Google Scholar] [CrossRef]
Halimi, Z.; Bavafa, A.; Cui, Q. Barriers to Community Connectivity: An Assessment of Reconnecting Communities Pilot Program. In Proceedings of the International Conference on Transportation and Development 2024, Atlanta, Georgia, 15–18 June 2024; pp. 83–91. [Google Scholar]
Morteza, A.; Yahyaeian, A.A.; Mirzaeibonehkhater, M.; Sadeghi, S.; Mohaimeni, A.; Taheri, S. Deep learning hyperparameter optimization: Application to electricity and heat demand prediction for buildings. Energy Build. 2023, 289, 113036. [Google Scholar] [CrossRef]
Barber, K.A.; Krarti, M. A review of optimization based tools for design and control of building energy systems. Renew. Sustain. Energy Rev. 2022, 160, 112359. [Google Scholar] [CrossRef]
Crawley, D.B.; Hand, J.W.; Kummert, M.; Griffith, B.T. Contrasting the capabilities of building energy performance simulation programs. Build. Environ. 2008, 43, 661–673. [Google Scholar] [CrossRef]
Suresh, K.; Thakur, D.C. Validazione e Valutazione Delle Performance dei Piani Ottimizzati di Manutenzione Ferroviaria Tramite Simulazione a Eventi Discreti. Performance Assessment and Validation of Railway Maintenance Optimized Plans via Discrete Event Simulations. 2021 Mar 30. Available online: https://unire.unige.it/handle/123456789/3469 (accessed on 3 March 2024).
Khodabandelu, A.; Park, J.W. Applications of Agent-Based Modeling (ABM) in Enhancing Facility Operation and Management. In Proceedings of the 9th International Conference on Construction Engineering and Project Management, Las Vegas, NV, USA, 20–23 June 2022; pp. 393–400. [Google Scholar]
Hafez, F.S.; Sa’di, B.; Safa-Gamal, M.; Taufiq-Yap, Y.H.; Alrifaey, M.; Seyedmahmoudian, M.; Stojcevski, A.; Horan, B.; Mekhilef, S. Energy Efficiency in Sustainable Buildings: A Systematic Review with Taxonomy, Challenges, Motivations, Methodological Aspects, Recommendations, and Pathways for Future Research. Energy Strategy Rev. 2023, 45, 101013. [Google Scholar] [CrossRef]
Qiang, G.; Tang, S.; Hao, J.; Di Sarno, L.; Wu, G.; Ren, S. Building automation systems for energy and comfort management in green buildings: A critical review and future directions. Renew. Sustain. Energy Rev. 2023, 179, 113301. [Google Scholar] [CrossRef]
Silva, R.D.A.; Braga, R.T.V. Simulating Systems-of-Systems with Agent-Based Modeling: A Systematic Literature Review. IEEE Syst. J. 2020, 14, 3609–3617. [Google Scholar] [CrossRef]
Abou Yassin, A.; Hamzeh, F.; Al Sakka, F. Agent based modeling to optimize workflow of robotic steel and concrete 3D printers. Autom. Constr. 2020, 110, 103040. [Google Scholar] [CrossRef]
Alabbasi, M.; Agkathidis, A.; Chen, H. Robotic 3D printing of concrete building components for residential buildings in Saudi Arabia. Autom. Constr. 2023, 148, 104751. [Google Scholar] [CrossRef]
Li, J.; Rombaut, E.; Vanhaverbeke, L. A systematic review of agent-based models for autonomous vehicles in urban mobility and logistics: Possibilities for integrated simulation models. Comput. Environ. Urban Syst. 2021, 89, 101686. [Google Scholar] [CrossRef]
Prakayaphun, T.; Hayashi, Y.; Vichiensan, V.; Takeshita, H. Identifying Impacts of School-Escorted Trips on Traffic Congestion and the Countermeasures in Bangkok: An Agent-Based Simulation Approach. Sustainability 2023, 15, 16244. [Google Scholar] [CrossRef]
Dabirian, S.; Moussazadeh, M.; Khanzadi, M.; Abbaspour, S. Predicting the effects of congestion on labour productivity in construction projects using agent-based modelling. Int. J. Constr. Manag. 2023, 23, 606–618. [Google Scholar] [CrossRef]
Zolfagharipoor, M.A.; Ahmadi, A. Agent-based modeling of participants’ behaviors in an inter-sectoral groundwater market. J. Environ. Manag. 2021, 299, 113560. [Google Scholar] [CrossRef]
Zhao, L.; Zhang, L.; Sun, J.; He, P. Can public participation constraints promote green technological innovation of Chinese enterprises? The moderating role of government environmental regulatory enforcement. Technol. Forecast. Soc. Chang. 2022, 174, 121198. [Google Scholar] [CrossRef]
Demartini, M.; Tonelli, F.; Govindan, K. An investigation into modelling approaches for industrial symbiosis: A literature review and research agenda. Clean. Logist. Supply Chain 2022, 3, 100020. [Google Scholar] [CrossRef]
Marvuglia, A.; Bayram, A.; Baustert, P.; Gutiérrez, T.N.; Igos, E. Agent-based modelling to simulate farmers’ sustainable decisions: Farmers’ interaction and resulting green consciousness evolution. J. Clean. Prod. 2022, 332, 129847. [Google Scholar] [CrossRef]
Liechty, J.C.; Mabey, C.S.; Mattson, C.A.; Salmon, J.L.; Weaver, J.M. Trade-Off Characterization Between Social and Environmental Impacts Using Agent-Based Product Adoption Models and Life Cycle Assessment. J. Mech. Des. 2022, 145, 032001. [Google Scholar] [CrossRef]
Herrera, M.; Pérez-Hernández, M.; Kumar Parlikad, A.; Izquierdo, J. Multi-Agent Systems and Complex Networks: Review and Applications in Systems Engineering. Processes 2020, 8, 312. [Google Scholar] [CrossRef]
Brugière, A.; Nguyen-Ngoc, D.; Drogoul, A. Handling multiple levels in agent-based models of complex socio-environmental systems: A comprehensive review. Front. Appl. Math. Stat. 2022, 8, 1020353. [Google Scholar] [CrossRef]
Lee, K.S.; Eom, J.K.; Moon, D. Applications of TRANSIMS in Transportation: A Literature Review. Procedia Comput. Sci. 2014, 32, 769–773. [Google Scholar] [CrossRef]
Auld, J.; Hope, M.; Ley, H.; Sokolov, V.; Xu, B.; Zhang, K. POLARIS: Agent-based modeling framework development and implementation for integrated travel demand and network and operations simulations. Transp. Res. Part C Emerg. Technol. 2016, 64, 101–116. [Google Scholar] [CrossRef]
Cenanï, Ş. Emergence and complexity in agent-based modeling: Review of state-of-the-art research. J. Comput. Des. 2021, 2, 1–24. [Google Scholar] [CrossRef]
Sharma, A.; Kosasih, E.; Zhang, J.; Brintrup, A.; Calinescu, A. Digital Twins: State of the art theory and practice, challenges, and open research questions. J. Ind. Inf. Integr. 2022, 30, 100383. [Google Scholar] [CrossRef]
Feng, K.; Li, Q.; Ellingwood, B.R. Post-earthquake modelling of transportation networks using an agent-based model. Struct. Infrastruct. Eng. 2020, 16, 1578–1592. [Google Scholar] [CrossRef]
Rezaei, Z.; Vahidnia, M.H.; Aghamohammadi, H.; Azizi, Z.; Behzadi, S. Digital twins and 3D information modeling in a smart city for traffic controlling: A review. J. Geogr. Cartogr. 2023, 6, 1865. [Google Scholar] [CrossRef]
Ye, X.; Du, J.; Han, Y.; Newman, G.; Retchless, D.; Zou, L.; Ham, Y.; Cai, Z. Developing Human-Centered Urban Digital Twins for Community Infrastructure Resilience: A Research Agenda. J. Plan. Lit. 2023, 38, 187–199. [Google Scholar] [CrossRef] [PubMed]
Latsou, C.; Farsi, M.; Erkoyuncu, J.A.; Morris, G. Digital Twin Integration in Multi-Agent Cyber Physical Manufacturing Systems. IFAC-PapersOnLine 2021, 54, 811–816. [Google Scholar] [CrossRef]
Dasgupta, S.; Rahman, M.; Lidbe, A.D.; Lu, W.; Jones, S. A Transportation Digital-Twin Approach for Adaptive Traffic Control Systems. arXiv 2021, arXiv:2109.10863. [Google Scholar]
Kashef, M.; Visvizi, A.; Troisi, O. Smart city as a smart service system: Human-computer interaction and smart city surveillance systems. Comput. Hum. Behav. 2021, 124, 106923. [Google Scholar] [CrossRef]
Williamson, S.M.; Prybutok, V. Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare. Appl. Sci. 2024, 14, 675. [Google Scholar] [CrossRef]
Darabi, N.; Hosseinichimeh, N. System dynamics modeling in health and medicine: A systematic literature review. Syst. Dyn. Rev. 2020, 36, 29–73. [Google Scholar] [CrossRef]
Lisiak-Myszke, M.; Marciniak, D.; Bieliński, M.; Sobczak, H.; Garbacewicz, Ł.; Drogoszewska, B. Application of Finite Element Analysis in Oral and Maxillofacial Surgery—A Literature Review. Materials 2020, 13, 3063. [Google Scholar] [CrossRef] [PubMed]
Shen, R.; Jiao, Z.; Parker, T.; Sun, Y.; Wang, Q. Recent application of Computational Fluid Dynamics (CFD) in process safety and loss prevention: A review. J. Loss Prev. Process Ind. 2020, 67, 104252. [Google Scholar] [CrossRef]
Li, W.; Zhou, H.; Lu, Z.; Kamarthi, S. Navigating the Evolution of Digital Twins Research through Keyword Co-Occurence Network Analysis. Sensors 2024, 24, 1202. [Google Scholar] [CrossRef]
Khanh, H.D.; Kim, S.-Y. Exploring Productivity of Concrete Truck for Multistory Building Projects Using Discrete Event Simulation. KSCE J. Civ. Eng. 2020, 24, 3531–3545. [Google Scholar] [CrossRef]
Ouda, E.; Sleptchenko, A.; Simsekler, M.C.E. Comprehensive review and future research agenda on discrete-event simulation and agent-based simulation of emergency departments. Simul. Model. Pract. Theory 2023, 129, 102823. [Google Scholar] [CrossRef]
Hussein, M.; Darko, A.; Eltoukhy, A.E.E.; Zayed, T. Sustainable Logistics Planning in Modular Integrated Construction Using Multimethod Simulation and Taguchi Approach. J. Constr. Eng. Manag. 2022, 148, 04022022. [Google Scholar] [CrossRef]
Winzar, H.; Baumann, C.; Soboleva, A.; Park, S.H.; Pitt, D. Competitive Productivity (CP) as an emergent phenomenon: Methods for modelling micro, meso, and macro levels. Int. J. Hosp. Manag. 2022, 105, 103252. [Google Scholar] [CrossRef]
Liang, X.; Luo, L.; Hu, S.; Li, Y. Mapping the knowledge frontiers and evolution of decision making based on agent-based modeling. Knowl. Based Syst. 2022, 250, 108982. [Google Scholar] [CrossRef]
Ibrahim, M.; Hashmi, U.S.; Nabeel, M.; Imran, A.; Ekin, S. Embracing Complexity: Agent-Based Modeling for HetNets Design and Optimization via Concurrent Reinforcement Learning Algorithms. IEEE Trans. Netw. Serv. Manag. 2021, 18, 4042–4062. [Google Scholar] [CrossRef]
Kaewmoracharoen, M.; Suwan, T.; Nusen, P.; Champrasert, P. Fitness-for-Use of As-Built Building Information Modeling for Digital Twin. In Proceedings of the 2022 37th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), Phuket, Thailand, 5–8 July 2022; pp. 868–871. [Google Scholar] [CrossRef]
Lu, Q.; Chen, L.; Li, S.; Pitt, M. Semi-automatic geometric digital twinning for existing buildings based on images and CAD drawings. Autom. Constr. 2020, 115, 103183. [Google Scholar] [CrossRef]
Furuta, S.; Nakazato, J.; Tsukada, M. Web-Based BIM Platform for Building Digital Twin. In Proceedings of the 2023 IEEE 3rd International Conference on Digital Twins and Parallel Intelligence (DTPI), Orlando, FL, USA, 7–9 November 2023; pp. 1–6. [Google Scholar] [CrossRef]
Sun, H.; Liu, Z. Research on Intelligent Dispatching System Management Platform for Construction Projects Based on Digital Twin and BIM Technology. Adv. Civ. Eng. 2022, 2022, e8273451. [Google Scholar] [CrossRef]
Sacks, R.; Brilakis, I.; Pikas, E.; Xie, H.S.; Girolami, M. Construction with digital twin information systems. Data-Centric Eng. 2020, 1, e14. [Google Scholar] [CrossRef]
Kaewunruen, S.; Peng, S.; Phil-Ebosie, O. Digital Twin Aided Sustainability and Vulnerability Audit for Subway Stations. Sustainability 2020, 12, 7873. [Google Scholar] [CrossRef]
Deng, M.; Menassa, C.C.; Kamat, V.R. From BIM to digital twins: A systematic review of the evolution of intelligent building representations in the AEC-FM industry. J. Inf. Technol. Constr. 2021, 26, 58–83. [Google Scholar] [CrossRef]
Rolfsen, C.N.; Lassen, A.K.; Han, D.; Hosamo, H.; Ying, C. The use of the BIM-model and scanning in quality assurance of bridge constructions. In ECPPM 2021-eWork and eBusiness in Architecture, Engineering and Construction; CRC Press: Boca Raton, FL, USA, 2021; pp. 357–360. Available online: https://books.google.com/books?hl=en&lr=&id=bcY5EAAAQBAJ&oi=fnd&pg=PA357&dq=info:LjR505EsuWoJ:scholar.google.com&ots=nV1TiMI65C&sig=5M3jp9KuahK1A_ID9h8aoaL3xiE (accessed on 3 March 2024).
Picco, M. Dynamic Energy Simulation Toward Integrated Design of Non-Residential Buildings Model Description Simplifications and Their Impact on Simulation Results; Università degli Studi di Bergamo: Bergamo, Italy, 2014; ISBN 978-88-97413-06-6. [Google Scholar]
Yan, D.; O’Brien, W.; Hong, T.; Feng, X.; Burak Gunay, H.; Tahmasebi, F.; Mahdavi, A. Occupant behavior modeling for building performance simulation: Current state and future challenges. Energy Build. 2015, 107, 264–278. [Google Scholar] [CrossRef]
Ahmed, O.; Sezer, N.; Ouf, M.; Wang, L.L.; Hassan, I.G. State-of-the-art review of occupant behavior modeling and implementation in building performance simulation. Renew. Sustain. Energy Rev. 2023, 185, 113558. [Google Scholar] [CrossRef]
Malik, J.; Azar, E.; Mahdavi, A.; Hong, T. A level-of-details framework for representing occupant behavior in agent-based models. Autom. Constr. 2022, 139, 104290. [Google Scholar] [CrossRef]
Uddin, M.N.; Chi, H.-L.; Wei, H.-H.; Lee, M.; Ni, M. Influence of interior layouts on occupant energy-saving behaviour in buildings: An integrated approach using Agent-Based Modelling, System Dynamics and Building Information Modelling. Renew. Sustain. Energy Rev. 2022, 161, 112382. [Google Scholar] [CrossRef]
Uddin, M.N. Occupant Behaviour Modeling for Building Energy Conservation: An Integrated Approach Using Agent Based, System Dynamics and Building Information Modeling. 2022. Available online: https://theses.lib.polyu.edu.hk/handle/200/11818 (accessed on 3 March 2024).
Sivakumar, N.; Mura, C.; Peirce, S.M. Innovations in integrating machine learning and agent-based modeling of biomedical systems. Front. Syst. Biol. 2022, 2, 959665. [Google Scholar] [CrossRef]
Arjomandnia, R.; Ilbeigi, M.; Kazemidemneh, M.; Hashemi, A.N. Renovating buildings by modelling energy–CO₂ emissions using particle swarm optimization and artificial neural network (case study: Iran). Indoor Built Environ. 2023, 32, 1621–1637. [Google Scholar] [CrossRef]
Ale Ebrahim Dehkordi, M.; Lechner, J.; Ghorbani, A.; Nikolic, I.; Chappin, É.; Herder, P. Using Machine Learning for Agent Specifications in Agent-Based Models and Simulations: A Critical Review and Guidelines. J. Artif. Soc. Soc. Simul. 2023, 26, 9. [Google Scholar] [CrossRef]
Augustijn, E.-W.; Abdulkareem, S.A.; Sadiq, M.H.; Albabawat, A.A. Machine Learning to Derive Complex Behaviour in Agent-Based Modellzing. In Proceedings of the 2020 International Conference on Computer Science and Software Engineering (CSASE), Duhok, Iraq, 16–18 April 2020; pp. 284–289. [Google Scholar] [CrossRef]
Deliu, N. Reinforcement learning for sequential decision making in population research. In Qual Quant; Springer: Berlin/Heidelberg, Germany, 2023. [Google Scholar] [CrossRef]
Moerland, T.M.; Broekens, J.; Jonker, C.M. Emotion in reinforcement learning agents and robots: A survey. Mach. Learn. 2018, 107, 443–480. [Google Scholar] [CrossRef]
Gilbert, T.K.; Lambert, N.; Dean, S.; Zick, T.; Snoswell, A.; Mehta, S. Reward Reports for Reinforcement Learning. In Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, Montreal, QC, Canada, 8–10 August 2023; Association for Computing Machinery: New York, NY, USA, 2023; pp. 84–130. [Google Scholar] [CrossRef]
Sidford, A.; Wang, M.; Wu, X.; Ye, Y. Variance reduced value iteration and faster algorithms for solving Markov decision processes. Nav. Res. Logist. NRL 2023, 70, 423–442. [Google Scholar] [CrossRef]
Cherrat, E.A.; Kerenidis, I.; Prakash, A. Quantum reinforcement learning via policy iteration. Quantum Mach. Intell. 2023, 5, 30. [Google Scholar] [CrossRef]
Sivamayil, K.; Rajasekar, E.; Aljafari, B.; Nikolovski, S.; Vairavasundaram, S.; Vairavasundaram, I. A Systematic Study on Reinforcement Learning Based Applications. Energies 2023, 16, 1512. [Google Scholar] [CrossRef]
Esteso, A.; Peidro, D.; Mula, J.; Díaz-Madroñero, M. Reinforcement learning applied to production planning and control. Int. J. Prod. Res. 2023, 61, 5772–5789. [Google Scholar] [CrossRef]
Yu, L.; Xiong, J.; Xie, M. GPI-Based design for partially unknown nonlinear two-player zero-sum games. J. Frankl. Inst. 2023, 360, 2068–2088. [Google Scholar] [CrossRef]
Ying, M.; Feng, Y.; Ying, S. Optimal Policies for Quantum Markov Decision Processes. Int. J. Autom. Comput. 2021, 18, 410–421. [Google Scholar] [CrossRef]
Gao, X.; Zhou, X. Logarithmic regret bounds for continuous-time average-reward Markov decision processes. arXiv 2022, arXiv:2205.11168. [Google Scholar] [CrossRef]
Yu, T.; Sra, S. Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation. arXiv 2019, arXiv:1907.09350. [Google Scholar]
Rai, S.; Hu, X. Hybrid agent-based and graph-based modeling for building occupancy simulation. In Proceedings of the Proceedings of the 4th ACM International Conference of Computing for Engineering and Sciences, Kuala Lumpur, Malaysia, 6–8 July 2018; Association for Computing Machinery: New York, NY, USA, 2018; pp. 1–12. [Google Scholar] [CrossRef]
Jenab, K.; Liu, D. A graph-based model for manufacturing complexity. Int. J. Prod. Res. 2010, 48, 3383–3392. [Google Scholar] [CrossRef]
Sahraoui, A.-E.-K.; Jayakrishnan, R. Microscopic-Macroscopic Models Systems Integration: A Simulation Case Study for ATMIS. Simulation 2005, 81, 353–363. [Google Scholar] [CrossRef]
Márquez, C.; César, E.; Sorribes, J. Graph-Based Automatic Dynamic Load Balancing for HPC Agent-Based Simulations. In Euro-Par 2015: Parallel Processing Workshops; Hunold, S., Costan, A., Giménez, D., Iosup, A., Ricci, L., Gómez Requena, M.E., Scarano, V., Varbanescu, A.L., Scott, S.L., Lankes, S., et al., Eds.; Springer International Publishing: Cham, Switzerland; Berlin, Germany, 2015; pp. 405–416. [Google Scholar]
Evolution of AEC Project Networks: An Agent-Based Modeling Approach—ProQuest. Available online: https://www.proquest.com/openview/451b43500a65d0f59cd9417da27be315/1?pq-origsite=gscholar&cbl=18750&diss=y (accessed on 3 March 2024).
Nourisa, J.; Zeller-Plumhoff, B.; Willumeit-Römer, R. CppyABM: An open-source agent-based modeling library to integrate C++ and Python. Softw. Pract. Exp. 2022, 52, 1337–1351. [Google Scholar] [CrossRef]
Giarola, S.; Sachs, J.; d’Avezac, M.; Kell, A.; Hawkes, A. MUSE: An open-source agent-based integrated assessment modelling framework. Energy Strategy Rev. 2022, 44, 100964. [Google Scholar] [CrossRef]
Antelmi, A.; Cordasco, G.; D’Ambrosio, G.; De Vinco, D.; Spagnuolo, C. Experimenting with Agent-Based Model Simulation Tools. Appl. Sci. 2023, 13, 13. [Google Scholar] [CrossRef]
Seid, M.; Bridgeland, D.; Bridgeland, A.; Hartley, D.M. A collaborative learning health system agent-based model: Computational and face validity. Learn. Health Syst. 2021, 5, e10261. [Google Scholar] [CrossRef] [PubMed]
Ogie, R.I.; O’Brien, S.; Federici, F.M. Towards using agent-based modelling for collaborative translation of crisis information: A systematic literature review to identify the underlying attributes, behaviours, interactions, and environment of agents. Int. J. Disaster Risk Reduct. 2022, 68, 102717. [Google Scholar] [CrossRef]
Thai, M.T.; Wu, W.; Xiong, H. Big Data in Complex and Social Networks; CRC Press: Boca Raton, FL, USA, 2016. [Google Scholar]
Halimi, Z.; SafariTaherkhani, M.; Cui, Q. A Generalized Framework for Assessing Equity in Ground Transportation Infrastructure: An Exploratory Study. arXiv 2024, arXiv:240919018. [Google Scholar]

Figure 1. Conceptual mind map for agent-based modeling (ABM) based on [15,16,17,18].

Figure 2. Topics related to ABM from 1970 to 2024.

Figure 3. Five-step methodological framework for a literature review on ABM in construction.

Figure 4. Experts’ survey results.

Figure 5. Heatmap visualizing the correlation analysis of ABM effectiveness ratings across various aspects as rated by the experts in the AEC industry.

Figure 6. Publication trend over time from 1989 to 2024, revealing a significant increase in ABM research within the AEC field from 1989 to 2024. The surge in publications, especially the peak around 2023, is attributed to technological advancements such as improved computational power and the integration of digital tools like BIM and digital twins.

Figure 7. Distribution of publications in the Top 10 academic journals by year range.

Figure 8. The top 10 topics by count in our dataset.

Figure 9. Distribution of journal articles published by country.

Figure 10. Exploring the multifaceted role of agent-based modeling in enhancing construction management and safety.

Figure 11. The interaction between market behavior, agent-based modeling (ABM), contextual experiments, and consumer behavior.

Figure 12. Chronological Progression of Life Cycle Stages with ABM Outputs and Their Market Impacts.

Figure 13. Conceptual framework for integrating machine learning (ML) with agent-based modeling (ABM)/multi-agent systems (MAS) to enhance decision-making processes at various levels.

Table 1. Agent-based modeling (ABM) across various academic fields, as identified in key papers.

Field	Key Findings	Reference
Environmental Science	Integrates behavioral factors with bio-economic modeling of agricultural production, enhancing the representation of farmers’ decision-making in response to changing conditions.	[42]
Social Science	Identifies the advancements needed in ABM to make it a mainstream method for exploring scenarios in complex socio-environmental systems.	[43]
Computer Science	Introduces Agents.jl, a performant Julia-based ABM software 6.1.10 that is less complex and more user-friendly than existing ABM tools, integrating seamlessly with the broader Julia ecosystem.	[44]
Economics	Proposes agent-based modeling as a vital tool for economic planning and forecasting, essential for sustainable development.	[7]
Climate-Energy Policy	Reviews ABM studies in climate-energy policy, emphasizing the need for behavioral assumptions and social network structures to analyze a broad spectrum of policies.	[45]
Biology	Surveys ABM applications in biology, from cellular to ecological levels, highlighting key results in plant growth, mortality, competition, and reproduction.	[46]
Engineering	Applies ABM to distributed graph analysis, providing an interactive environment for agent-based graph programming and aiding in the discovery of significant structural attributes of networks.	[47]
Land Use	Suggests conceptual approaches for implementing ABM across scales, using big data to simulate Social-Ecological-Systems (SESs) for policy analysis.	[48]
Ecology	Discusses the role of ABM in understanding complex systems, comparing it with traditional models, and outlining the challenges and opportunities in the field, especially with the integration of data science and AI.	[2]
Banking and Economy	Examines how agent-based banking models can support financial inclusion and sustainability in emerging markets and developing economies, contributing to the global development through economic circularity.	[49]

Table 2. Agent-based modeling (ABM) across various academic fields, as identified in key papers.

Feature	Objectives	Reference
Lean Construction Principles	Enhance traditional project management processes	[96,97]
	Integrate BIM into LC for improved project outcomes	[98,99]
	Utilize digital tools for lean construction development	[100]
	Framework for selecting lean tools based on objectives and functionalities	[101]
	Enhance efficiency and integration in construction management through BIM and lean principles synergy	[102,103]
Efficiency Optimization	Improve construction site productivity and quality	[104,105]
	Leverage ABM for construction waste management complexity	[106]
	Enhance lean and green project outcomes through BIM	[107,108]
	Improve construction productivity through integration of lean concept and heuristic models	[109,110]

Table 3. Categorization of research on process planning.

Major Trends	Reference	Objectives
ABM for Complex Logistics	[127]	ABM application to handle complex adaptive systems in construction waste management.
Dynamic ABM Simulation	[1]	Capturing recent ABM development in construction research for dynamic simulation.
ABM in Safety Management	[128]	Using BIM and ABM for planning and managing safety in construction processes.
Lean Construction and ABM	[99]	Synergy of BIM and Lean Construction enhanced by ABM for efficiency in public projects.
ABM for Process Improvement	[129]	The use of ABM in developing a Digital Obeya Room framework for visual construction management.

Table 4. Overview of construction safety classifications that has potential synergy with agent-based modeling (ABM).

Feature	Objectives	Reference
Worker Behavior Modeling	Identify recurring behavioral patterns leading to accidents and develop interventions	[160,161]
	Forecast and modify unsafe behaviors through predictive modeling	[162]
	Explore the impact of safety climate and interpersonal relationships on safety behavior	[163]
	Improve understanding of team processes and their effects on worker safety	[164]
Accident Prevention Strategies	Develop and implement safety archetypes for construction safety management	[161]
	Explore rules for accident prevention based on unsafe behaviors and apply association rules for prevention	[165]
	Utilize computer vision technology for real-time monitoring and identification of risky behaviors	[166]
	Apply building information Modeling (BIM) for integrating safety measures from design to construction site management	[128]

Table 5. Overview of research studies on the integration of ABM within digital twin applications across various construction and building management scenarios.

Study Title	Application Area	Potential ABM Integration
[232]	Building Management	ABM could simulate occupant behaviors (e.g., movement, energy usage) within the DT to optimize building operations and energy efficiency.
[233]	Construction and Renovation	Use ABM to model the interactions of construction agents (workers, machinery) to enhance project scheduling and resource allocation in the renovation process.
[234]	Facility Management	Implement ABM to simulate the dynamic maintenance requirements and operational tasks of building components, improving lifecycle management.
[235]	Construction Project Management	Integrate ABM to simulate the decision-making process of project managers and the impact of dispatching strategies on project timelines and resource efficiency.
[236]	Construction and Operations	Apply ABM to explore how different construction scenarios (e.g., supply chain disruptions, workforce dynamics) affect project outcomes and operational efficiency.
[237]	Infrastructure Management	Utilize ABM to assess the impact of human behaviors and system interactions on the sustainability and vulnerability of subway stations, aiding in emergency planning and resource optimization.
[238]	AEC-FM Industry	ABM could be used to simulate stakeholder interactions within the DT environment to identify and address bottlenecks in information flow and collaboration.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

© 2024 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

Share and Cite

MDPI and ACS Style

Mazzetto, S. Interdisciplinary Perspectives on Agent-Based Modeling in the Architecture, Engineering, and Construction Industry: A Comprehensive Review. Buildings 2024, 14, 3480. https://doi.org/10.3390/buildings14113480

AMA Style

Mazzetto S. Interdisciplinary Perspectives on Agent-Based Modeling in the Architecture, Engineering, and Construction Industry: A Comprehensive Review. Buildings. 2024; 14(11):3480. https://doi.org/10.3390/buildings14113480

Chicago/Turabian Style

Mazzetto, Silvia. 2024. "Interdisciplinary Perspectives on Agent-Based Modeling in the Architecture, Engineering, and Construction Industry: A Comprehensive Review" Buildings 14, no. 11: 3480. https://doi.org/10.3390/buildings14113480

APA Style

Mazzetto, S. (2024). Interdisciplinary Perspectives on Agent-Based Modeling in the Architecture, Engineering, and Construction Industry: A Comprehensive Review. Buildings, 14(11), 3480. https://doi.org/10.3390/buildings14113480

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu