{
  "id": 13464,
  "url": "https://arxiv.org/abs/2607.21557v1",
  "title": "OpenForgeRL: Train Harness-native Agents in Any Environment",
  "summary": "Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with open infrastructure, whose SFT/RL stacks cannot natively express stateful, multi-process harness inference. To address this, we present OpenForgeRL, an open-source framework for training harness-based agents end-to-end in diverse environments.",
  "authors": "Xiao Yu, Baolin Peng, Ruize Xu, Hao Zou, Qianhui Wu, Hao Cheng, Wenlin Yao, Nikhil Singh, Zhou Yu, Jianfeng Gao",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-23T17:38:30.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/13464",
  "original_url": "https://arxiv.org/abs/2607.21557v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}