{
  "id": 9256652,
  "title": "Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents",
  "url": "https://urgent.news/2026/09/22/grow-the-harness-not-the-context-from-strategy-free-scaffolds-to",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T17:40:45.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.26760v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task's context. We study whether task feedback can instead turn recurring control into reusable executable code, while reserving LLM calls for task-specific semantic reasoning. We introduce Growing Harness, a failure-guided…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}