AI RESEARCH
Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering
arXiv CS.AI
•
ArXi:2604.27724v1 Announce Type: new Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose MED-VRAG, an iterative multimodal RAG framework that retrieves and reasons over PMC document page images instead of OCR'd text.