ClawGym II: Black-Box RL Stably Optimizes Agents Through Complex Harnesses

RUC · hf · 2026-08-18

RUC releases ClawGym II, a unified black-box RL framework that enables stable, scalable optimization of general agents operating through complex harnesses via sandbox execution, trajectory reconstruction, and mix-harness training, without white-box model access.

Related event: RUC's ClawGym II Trains Agents via Black-Box RL on Real Harnesses(3 posts)→

Original post →

More from coding & agent

coding & agent channel →