Moves medical AI from simplified 2D image classification to agents navigating full 3D clinical studies.
March 27, 2026
Original Paper
MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies
arXiv · 2603.24649
The Takeaway
It introduces a runtime for VLMs to interact with professional medical viewers and reveals that current models fail at spatial grounding when given actual clinical tools, establishing a new frontier for medical AI deployment.
From the abstract
Currently, evaluating vision-language models (VLMs) in medical imaging tasks oversimplifies clinical reality by relying on pre-selected 2D images that demand significant manual labor to curate. This setup misses the core challenge of realworld diagnostics: a true clinical agent must actively navigate full 3D volumes across multiple sequences or modalities to gather evidence and ultimately support a final decision. To address this, we propose MEDOPENCLAW, an auditable runtime designed to let VLMs