Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents

[arXiv] [PDF]

The Agent Trading Arena is a closed-loop, prior-free human-like trading environment designed to evaluate and advance self-play-capable financial agents.

Preparation

Python Install

git clone https://github.com/wekjsdvnm/Agent-Trading-Arena
cd Agent-Trading-Arena
pip install -r requirement.txt

Set OpenAI API Key:

Export your OpenAI API key as an environment variable. Replace "your_OpenAI_API_key" with your actual API key.

cd Stock_Main/content/utils.py
openai_api_key = "your_OpenAI_API_key"

OA_OPENAI_KEY is the OpenAI API key. You can get it from the OpenAI.

Experiment

Run the code

cd Agent-Trading-Arena
sh run.sh

Citation

If you find our work useful, please consider citing us!

@misc{ma2025agenttradingarena,
      title={Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents}, 
      author={Tianmi Ma and Jiawei Du and Wenxin Huang and Wenjie Wang and Liang Xie and Xian Zhong and Joey Tianyi Zhou},
      year={2025},
      journal={arXiv preprint arXiv: 2502.17967},
}