面向放射学视觉问答中复杂推理的多智能体系统
A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering
AI总结：
本文提出一个多智能体系统，通过上下文理解、多模态推理和答案验证三个专门智能体，解决放射学视觉问答中事实准确性和幻觉问题，实验证明其优于强MLLM基线，支持可解释的临床AI应用。
摘要：
放射学视觉问答（RVQA）为关于胸部X光图像的问题提供精确答案，从而减轻放射科医生的工作负担。尽管基于多模态大语言模型（MLLMs）和检索增强生成（RAG）的最新方法在RVQA中展现出有前景的进展，但它们仍面临事实准确性、幻觉和跨模态错位方面的挑战。我们引入了一个多智能体系统（MAS），旨在支持RVQA中的复杂推理，该系统包含专门用于上下文理解、多模态推理和答案验证的智能体。我们在一个具有挑战性的RVQA测试集上评估了我们的系统，该测试集通过模型分歧过滤方法构建，包含多个MLLMs一致认为困难的案例。大量实验证明了我们的系统相对于强MLLM基线的优越性和有效性，案例研究展示了其可靠性和可解释性。这项工作凸显了多智能体方法在支持需要复杂推理的可解释且可信的临床AI应用方面的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
