{
  "id": 222,
  "url": "https://arxiv.org/abs/2607.05458v1",
  "title": "Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning",
  "summary": "Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infrastructure. We argue that this harness is itself a learnable control layer. We formalize harness operation as a finite-horizon Harness MDP, where a lightweight controller selects structural execution actions while the LLM executor remains frozen. The controller is trained from offline rollouts using advantage-weighted ",
  "authors": "Haiwen Yi, Xinyuan Song",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-05T22:11:18.000Z",
  "fetched_at": "2026-07-14T14:14:24.246Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/222",
  "original_url": "https://arxiv.org/abs/2607.05458v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}