{
  "id": 17340,
  "url": "https://arxiv.org/abs/2608.06197v1",
  "title": "EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning",
  "summary": "Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verification are costly, or on external simulators that are difficult to ground. We introduce EnvACE, an agentic reinforcement learning method that replaces external environment interaction during training with world rehearsal. The policy alternates between acting and rehearsal: it first generates a tool call, then plays the role",
  "authors": "Zishan Xu, Zhiyuan Yao, Yuxin Chen, Yifu Guo, Zhengxi Lu, Yuquan Lu, Jinyang Huang, Yan Xu, Yasheng Wang, Weinan Zhang, Xingshan Zeng, Weiwen Liu",
  "category": "research",
  "topics": "regulation,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T15:54:36.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "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/17340",
  "original_url": "https://arxiv.org/abs/2608.06197v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}