by StigLidu · Agent Tool · ★ 23
Generalizable End-to-End Tool-Use RL with Synthetic CodeGym Weihua Du, Hailei Gong, Zhan Ling, Kang Liu, Lingfeng Shen, Xuesong Yao, Yufei Xu, Dingyuan Shi, Yiming Yang, Jiecao Chen "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym" (2025) CodeGym is a synthetic environment generation framework for LLM agent reinforcement learning on multi-turn tool-use tasks. It automatically converts static code problems into interactive CodeGym environments where agents can learn to use tools to solve complex tasks in various configurations.
| Stars | 23 |
| Forks | 2 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 64.3213835630862/100 |
| Last Updated | 2025-10-14 |
| Created | 2025-09-18 |
| Platforms | python |
| Est. Tokens | ~71k |
Explore other popular agent tool tools:
CodeGym is The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym". It is categorized as a Agent Tool with 23 GitHub stars.
CodeGym is primarily written in Python. It covers topics such as llm-agent, reinforcement-learning, reinforcement-learning-environments.
You can find installation instructions and usage details in the CodeGym GitHub repository at github.com/StigLidu/CodeGym. The project has 23 stars and 2 forks, indicating an active community.