WooooDyy/AgentGym-RL

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

52
/ 100
Established

This framework helps developers train large language model (LLM) agents to make intelligent decisions over many steps in real-world scenarios. It takes an LLM and training data from diverse environments as input, and outputs an enhanced LLM agent capable of multi-turn interactions that can match or surpass commercial models. Machine learning researchers and practitioners focused on agent development would use this.

635 stars.

Use this if you need to train LLM agents for complex, long-horizon tasks requiring multiple interactions with an environment, and want to use reinforcement learning to improve their performance.

Not ideal if you are looking for a pre-trained agent for single-turn tasks or if you do not have a background in machine learning and reinforcement learning.

LLM-agent-training reinforcement-learning multi-turn-decision-making AI-agent-development interactive-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

635

Forks

63

Language

Python

License

MIT

Last pushed

Feb 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/WooooDyy/AgentGym-RL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.