{
  "schema_version": "1.0",
  "id": "archive:https://arxiv.org/abs/2607.09654v1",
  "slug": "2607-09654v1-0b5dedg",
  "url": "https://feed7.dev/p/2607-09654v1-0b5dedg",
  "title": "Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models",
  "why_included": "A decade-spanning VLM study finds modern models approach top human scene-description accuracy, while spatial attention differences remain a useful failure signal.",
  "summary": "**The gist** Researchers tested **nine VLMs from 2017–2025** and **20 human descriptions** on **100 Complex Social Behavior images**, tracking five visual-cognitive error types.",
  "practical_implication": "**Why it matters** For image-aware agents, evaluation should include **complex social scenes** and separate detection, recognition, hallucination, scene-understanding, and spatial-dependence failures instead of relying only on aggregate accuracy.",
  "agent_context": "**The gist** Researchers tested **nine VLMs from 2017–2025** and **20 human descriptions** on **100 Complex Social Behavior images**, tracking five visual-cognitive error types.\n\n**Why it matters** For image-aware agents, evaluation should include **complex social scenes** and separate detection, recognition, hallucination, scene-understanding, and spatial-dependence failures instead of relying only on aggregate accuracy.\n\n**Watch out** The conclusions come from **CSB plus an MS-COCO sample**. Modern models still sometimes base descriptions on different image regions than humans, labeled **spatial dependence error**.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2607.09654v1",
    "published_at": null
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "benchmark",
  "domains": [
    "image",
    "research"
  ],
  "topics": [
    "agent-evals",
    "benchmark-integrity",
    "agent-reliability"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The conclusions come from **CSB plus an MS-COCO sample**. Modern models still sometimes base descriptions on different image regions than humans, labeled **spatial dependence error**."
  ],
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2607-09654v1-0b5dedg",
    "json": "https://feed7.dev/p/2607-09654v1-0b5dedg.json",
    "markdown": "https://feed7.dev/p/2607-09654v1-0b5dedg.md"
  }
}