{
  "id": 3928,
  "url": "https://arxiv.org/abs/2605.22166v2",
  "title": "Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents",
  "summary": "LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights o",
  "authors": "Tianshi Xu, Huifeng Wen, Meng Li",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-21T08:36:49.000Z",
  "fetched_at": "2026-07-14T16:30:36.743Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3928",
  "original_url": "https://arxiv.org/abs/2605.22166v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}