{
  "id": 7009,
  "url": "https://arxiv.org/abs/2603.18894v1",
  "title": "I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems",
  "summary": "Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that integrity in institutional AI should be treated as a pre-deployment requirement rather than a post-deployment assumption. We evaluate multi-agent governance simulations in which agents occupy formal governmental roles under different authority structures, and we s",
  "authors": "Vedanta S P, Ponnurangam Kumaraguru",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-19T13:34:54.000Z",
  "fetched_at": "2026-07-14T16:32:54.534Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7009",
  "original_url": "https://arxiv.org/abs/2603.18894v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}