AgentGym-RL and MedAgentGym
About AgentGym-RL
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.
About MedAgentGym
wshi83/MedAgentGym
[ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale
This training environment is designed to improve how large language models (LLMs) can reason and generate code for medical tasks. It takes anonymized electronic health record (EHR) data and medical task descriptions, then evaluates the LLM's ability to produce correct, executable code for medical reasoning problems. Researchers and AI developers focused on medical AI would use this to build more capable AI assistants for healthcare.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work