{
  "id": 18267,
  "url": "https://arxiv.org/abs/2608.09638v1",
  "title": "Avalon-ToM-Bench: Evaluating Fine-Grained Theory of Mind via Asymmetric Game Mechanics",
  "summary": "Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reasoning or interactive settings that provide limited diagnostic insight. We present Avalon-ToM-Bench, a fine-grained benchmark that operationalizes ToM through the asymmetric-information mechanics of The Resistance: Avalon. Rather than evaluating end-to-end gameplay, it decomposes ToM into a 2$\\times$2 taxonomy -- epistemic versus motivational reason",
  "authors": "Yen-Shan Chen, Yu Chian Duan, Chih-En Kuo, Jian-Bin Wu, Yun-Nung Chen",
  "category": "research",
  "topics": "healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T14:19:08.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18267",
  "original_url": "https://arxiv.org/abs/2608.09638v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}