We present Workforce, a hierarchical multi-agent framework that decouples planning from execution through a modular architecture with a domain-agnostic Planner, Coordinator, and specialized Workers. This enables cross-domain transfer by allowing worker modification without full system retraining. On the GAIA benchmark, Workforce achieves state-of-the-art 69.70% accuracy, outperforming commercial systems.
This repository contains inference part code for the OWL framework (Workforce).
The camel version we use is 0.2.46. To reproduce Workforce inference performance on GAIA benchmark (69.70% - Claude-3.7 accuracy on GAIA benchmark, pass@1, and 60.61% - GPT-4o accuracy on GAIA benchmark, pass@3), follow the steps below:
- Create a Python 3.11 Conda environment:
conda create -n owl python=3.11- Install the required packages:
pip install -r requirements.txt- Set up envionment variables:
copy .env.example to .env and set the environment variables, and set the keys in .env file.
- Run the inference:
- For reproducing results using GPT-4o, run:
python run_gaia_workforce.py- For reproducing results using Claude-3.7, run:
python run_gaia_workforce_claude.py