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.
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.
Stars
635
Forks
63
Language
Python
License
MIT
Category
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.
Compare
Related tools
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
sethkarten/LLM-Economist
Official repository of the 2025 paper, LLM Economist: Large Population Models and Mechanism...