Welcome to our code repository for the Multi Agent Hackathon! This hackathon focused on discovery the failure in the multi-agent systems. Our team worked on Scaling Laws of LLM Cooperation, and this repository provides an in-depth look at our code and results.

Our exploration answer a interesting question that, will the failure cases exacerbate as the number of agents increases? To demonstrate this, we let LLMs play the n-player Prisoner‘s Dilemma, our results demonstrate that the LLM agents experienced unintended failure as the scale of agents increased.

git clone [email protected]:ReedZyd/MultiAgentHackathon.git
cd MultiAgentHackathon
pip install -r requirements.txt

1. To run single-round game:

python test_nPrisoners.py

2. To run multiple-round game:

python test_nPrisoners.py --repeated-game

3. To use ChatGPT API 'gpt-4', please add --gpt gpt-4