{
  "id": 14423,
  "url": "https://arxiv.org/abs/2607.25933v1",
  "title": "Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases",
  "summary": "Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practice, including progressive disclosure of multimodal information, dynamic updating of diagnostic hypotheses, and continuous refinement of clinical reasoning. However, existing evaluations of multimodal large language models (MLLMs) typically rely on single-turn or isolated tasks, making it difficult to fully capture the complexity of real-world clinic",
  "authors": "Rui Yang, Weihao Xuan, Yi Lin, Zhuhan Bao, Jonathan Chong Kai Liew, Matthew Yu Heng Wong, Nicolás Lescano, Nikita R. Paripati, Emily Ling-Lin Pai, Jiarui Liu, Heli Qi, Heng-Jui Chang, Benny Kai Guo Loo, Huitao Li, Kunyu Yu, Yufan Wang, Chuan Hong, Shijian Lu, Douglas Teodoro, Naoto Yokoya, Ross Koppel, Mona Diab, Hua Xu, David W. Bates, Nan Liu, Yifan Peng",
  "category": "research",
  "topics": "healthcare,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-28T16:19:03.000Z",
  "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/14423",
  "original_url": "https://arxiv.org/abs/2607.25933v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}