{
  "id": 1350,
  "url": "https://arxiv.org/abs/2606.07805v1",
  "title": "Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems",
  "summary": "The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluation frameworks neglect procedural compliance, leading to ''Machiavellian'' behaviors where agents strategically violate safety rules to maximize rewards - a direct manifestation of Goodhart's Law. To address this blind spot, we introduce MAC-Bench, a dynamic, adversarial benchmark designed to evaluate the procedural ali",
  "authors": "Yiyang Zhao, Zhuo Zhang, Qingxuan Le, Lizhen Qu, Zenglin Xu",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-05T19:33:58.000Z",
  "fetched_at": "2026-07-14T14:15:12.457Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1350",
  "original_url": "https://arxiv.org/abs/2606.07805v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}