{
  "id": 5954,
  "url": "https://arxiv.org/abs/2604.11174v1",
  "title": "EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems",
  "summary": "Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation accuracy. These metrics leave a critical gap: they do not measure whether embodied systems are governable -- whether they respect capability boundaries, enforce policies, recover safely, maintain audit trails, and respond to human oversight. We present EmbodiedGovBe",
  "authors": "Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li",
  "category": "research",
  "topics": "regulation,agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-13T08:34:04.000Z",
  "fetched_at": "2026-07-14T16:32:06.471Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5954",
  "original_url": "https://arxiv.org/abs/2604.11174v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}