Saved in:
Bibliographic Details
Main Authors: Yi, Ziruo, Liu, Jinyu, Xiao, Ting, Albert, Mark V.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.02841
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Radiology visual question answering (RVQA) provides precise answers to questions about chest X-ray images, alleviating radiologists' workload. While recent methods based on multimodal large language models (MLLMs) and retrieval-augmented generation (RAG) have shown promising progress in RVQA, they still face challenges in factual accuracy, hallucinations, and cross-modal misalignment. We introduce a multi-agent system (MAS) designed to support complex reasoning in RVQA, with specialized agents for context understanding, multimodal reasoning, and answer validation. We evaluate our system on a challenging RVQA set curated via model disagreement filtering, comprising consistently hard cases across multiple MLLMs. Extensive experiments demonstrate the superiority and effectiveness of our system over strong MLLM baselines, with a case study illustrating its reliability and interpretability. This work highlights the potential of multi-agent approaches to support explainable and trustworthy clinical AI applications that require complex reasoning.