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.

An AI doctor agent trained to master two core skills of a human physician: dynamic inquiry and decison-making, based on experiential agentic reinforcement learning.

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

GPU time-sharing for concurrent LLM RL

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