{
  "id": 14426,
  "url": "https://arxiv.org/abs/2607.25921v1",
  "title": "Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA",
  "summary": "In this work, we study the use of Vision-Language Models (VLMs) for anomaly detection in an agent-driven game Quality Assurance (QA) pipeline focusing on geometry clipping. In this evaluation, a custom exploration agent navigates a game level to collect visual observations, while the automatic annotation pipeline provides frame-level clipping labels. This setup allows us to evaluate recent VLMs on a controlled anomaly detection task without manual annotation. We benchmark six recent VLMs (Gemini",
  "authors": "Carlos Celemin, Benedict Wilkins, Adrián Barahona-Ríos, Saman Zadtootaghaj, Nabajeet Barman",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": "google",
  "regions": null,
  "published_at": "2026-07-28T16:10:47.000Z",
  "fetched_at": "2026-07-29T05:10:12.205Z",
  "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/14426",
  "original_url": "https://arxiv.org/abs/2607.25921v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}