{
  "id": 15702424,
  "title": "OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory",
  "url": "https://urgent.news/2026/10/19/openvlharness-real-world-visual-agentic-tool-use-with-multimodal",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-19T17:59:58.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.26860v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks shows that simply increasing the inference budget of the base model yields only modest gains. Such tasks demand grounded perception, external knowledge, and numerical measurements…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}