{
  "id": 9068362,
  "title": "ActGov: Governing LLM Agent Actions via Policy-Constrained Validation",
  "url": "https://urgent.news/2026/09/21/actgov-governing-llm-agent-actions-via-policy-constrained-validation",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-21T11:47:09.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.24446v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing defenses isolate injected content or constrain execution with predefined plans and static policies, but these approaches are brittle under dynamic workflows and scale poorly across extensible tool…",
  "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."
}