AgentGym

Build and run agents you can see, understand and trust.

Optimizing inference proxy for LLMs

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

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.