Projects sharing features with EEPO

✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

ICLR 2026 Agentic Reinforced Policy Optimization (ARPO)

G2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance

Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is based on OpenRLHF

DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal

```bash conda create -n rllm python=3.10 -y conda activate rllm

DAPO: an Open-source RL System from ByteDance Seed and Tsinghua AIR

The official repository for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning".