Rstar2 Agent Reasoning

Train efficient 14B-parameter agents via GRPO with resample-on-correct rollout strategy and Python code execution, achieving state-of-the-art reasoning through autonomous exploration and iterative refinement

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 23f8932815

Frequently asked questions

npx get-skill add adu2021/rstar2-agent-reasoning