{
  "id": 11077215,
  "title": "MADBench: Benchmarking the Security of Multi-Agent Debate",
  "url": "https://urgent.news/2026/09/30/madbench-benchmarking-the-security-of-multi-agent-debate",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-30T07:12:59.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.39146v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Multi-agent debate (MAD) can improve large language model (LLM) reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect answer. Although some efforts have been made to examine particular attack types on MAD, systematic…",
  "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."
}