Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

Run more RL experiments. Wait less for GPUs.

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Claw-R1: Empowering OpenClaw with Advanced Agentic RL.

DART-GUI: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

Proximity-based Multi-turn Optimization (ProxMO) - Official Implementation

SGLang model provider for Strands Agents for on-policy agentic RL training.

Standardizing environment infrastructure with Strands Agents — step, observe, reward.

This is the official repository for our paper "Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning" published in ICRL 2026.

Official Code of Paper: MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization

Official implementation for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe"

Train and customize OpenClaw agents using reinforcement learning with simple language feedback and fully asynchronous optimization.