{
  "id": 527044,
  "title": "Multi-Agent AI Safety as an Institutional Design Problem",
  "url": "https://urgent.news/2026/08/10/multi-agent-ai-safety-as-an-institutional-design-problem",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-10T16:47:01.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.09828v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent work already shows that deployment rules can change collective behavior. Here we ask which parts of an AI institution produce safety and how they do it. This is the first paper from POLIS, an ongoing research programme studying algorithmic…",
  "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."
}