Important
✨ Welcome to visit the GenMentor website to learn more about our work!
These are the supplementary resources of our paper "LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System", accepted by WWW 2025 (Industry Track) as an Oral Presentation.
In this paper, we propose GenMentor, a large language model (LLM)-powered multi-agent framework designed for goal-oriented learning in Intelligent Tutoring Systems (ITS). This framework emphasizes personalization, adaptive learning, and goal-aligned content delivery, making it a robust solution for professional and lifelong learning scenarios.
Note
We will release more available resources (code and data) in future updates, which are still under the internal review process of Microsoft. Stay tuned!
Welcome to explore the demo version of the GenMentor web application:
Note
Due to Microsoft's policy, please click here to send an email to join the whitelist of the GenMentor demo.
This interactive demo showcases GenMentor's core functionalities, including:
- Skill Gap Identification: Precisely map learner goals to required skills.
- Adaptive Learner Modeling: Capture learner progress and preferences.
- Personalized Content Delivery: Generate tailored learning resources.
You could also watch the demo video for a quick overview (click the image below):
- Skill Gap Identifier (
prompts/skill_gap_identification) - Adaptive Learner Modeler (
prompts/adaptive_learner_modeling) - Learning Path Scheduler (
prompts/learning_path_scheduling) - Tailored Content Generator (
prompts/tailored_content_creation)
@inproceedings{wang2025llm,
title={LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System},
author={Wang, Tianfu and Zhan, Yi and Lian, Jianxun and Hu, Zhengyu and Yuan, Nicholas Jing and Zhang, Qi and Xie, Xing and Xiong, Hui},
booktitle={Companion Proceedings of the ACM Web Conference},
year={2025}
}