AINewsnow

MLLMs Fail to Refuse when Using Tools Agentically

arXiv:2610.03938v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) have recently pushed the frontier of visual reasoning by calling tools such as zooming and tagging. Despite the recent strong success of agentic MLLMs, this work uncovers a critical safety failure in th…

Read the full story at arXiv cs.AI ↗

Timeline · 1 report

  1. 2026-10-07 04:00 · arXiv cs.AI
    MLLMs Fail to Refuse when Using Tools Agentically

More stories

  1. Introducing Mistral Large 4 — Mistral AI News
  2. EmbeddingGemma 2: an open, lightweight multimodal embedding model — Google DeepMind Blog
  3. Sharing AI progress in mathematics — OpenAI News
  4. Mistral Says Its New AI Model ‘Le Chonk’ Is the Best Open-Weight Offering Outside of China — Wired AI
  5. Trump’s big AI move: ‘Super Intelligence Force’ launched, Jay Clayton named AI czar — Mint AI
  6. OpenAI safety leader quits, warning AI company’s culture is ‘broken’ — The Guardian AI
  7. Together Link: open models in the harness you already use. Start with one command today. — Together AI Blog
  8. OpenAI agents tried to hack Wikipedia tools and flooded it with traffic — Ars Technica AI

Get the daily brief of stories like this at 6:30 every morning →