OpenForgeRL: Train Harness-native Agents in Any Environment
- Published
- Source
- arXiv
- Paper number
- 707
- Field
- AI / General
- arXiv ID
- 2607.21557
Key points
- It records harness model calls as proxies so standard RL code, such as veRL, can train on them.
- Each rollout is isolated in a Kubernetes container, allowing complex environments to run safely.
- Training and deployment share the same harness, eliminating train-deploy mismatch.
- OpenForge-Claw reaches 55.9 pass@3 on ClawEval, and OpenForge-GUI reaches 37.7 on OSWorld.
- RL improves self-verification and tool coverage, but error recovery remains weak.
Paper links
External research summaries. These are not HDATF publications or measured product results.