GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI

GAZE is a framework enabling medical Vision-Language Models (VLMs) to iteratively analyze brain MRI images using viewer-level tools and literature retrieval. It achieved 58.2 mAP for lesion localization and 34.9% Top-1 diagnostic accuracy on the NOVA benchmark for rare neurological conditions.