{
  "id": 7386,
  "url": "https://arxiv.org/abs/2603.10577v2",
  "title": "CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents",
  "summary": "Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment by perceiving high-level natural-language instructions. As such agents become increasingly capable and are deployed across diverse desktop environments, evaluating their behavior in a scalable and reliable manner becomes a critical challenge. Existing evaluation pipelines rely on static benchmarks, rule-based success checks, or manual inspection, ",
  "authors": "Marta Sumyk, Oleksandr Kosovan",
  "category": "research",
  "topics": "agents-autonomy,transparency,environment",
  "orgs": "meta",
  "regions": null,
  "published_at": "2026-03-11T09:28:41.000Z",
  "fetched_at": "2026-07-14T16:33:12.389Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7386",
  "original_url": "https://arxiv.org/abs/2603.10577v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}