CARE：迈向多模态医学推理中的临床问责的证据基础代理框架
CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
AI总结：
CARE通过证据基础的代理框架提升多模态医学推理的准确性与问责性，结合解耦的专业模型和明确证据，实现更可靠的医学AI。
摘要：
大型视觉语言模型（VLMs）在多模态医学推理方面表现出强大的能力，但大多数模型以端到端的黑箱方式运作，偏离了医生基于证据的分阶段工作流程，阻碍了临床问责。互补地，专家视觉定位模型能够准确地定位感兴趣区域（ROIs），提供明确、可靠的证据，从而提高推理准确性和信任度。在本文中，我们介绍了CARE，通过证据基础的代理框架，推进多模态医学推理中的临床问责。与现有方法将定位和推理结合在单一通用模型中不同，CARE将任务分解为协调的子模块，以减少捷径学习和幻觉：一个紧凑的VLM提出相关的医学实体；一个专家实体指引用分割模型生成像素级的ROIs证据；一个基于证据的VLM在由ROIs提示增强的完整图像上进行推理。VLMs通过具有可验证奖励的强化学习进行优化，以使答案与支持证据对齐。此外，一个VLM协调器计划工具调用并审查证据-答案一致性，提供代理控制和最终验证。在标准医学VQA基准测试上，我们的CARE-Flow（无协调器）在相同大小（10B）的当前最佳（SOTA）基础上将平均准确率提高了10.9%。随着动态规划和答案审查，我们的CARE-Coord进一步提升了性能，超越了大量预训练的SOTA，提高了5.2%。我们的实验表明，一个模拟临床工作流程的代理框架，结合解耦的专业模型和明确的证据，能够产生更准确和可问责的医学AI。项目页面：https://xypb.github.io/CARE-Project-Page/
英文摘要：
Large visual language models (VLMs) have shown strong multi-modal medical reasoning ability, but most operate as end-to-end black boxes, diverging from clinicians' evidence-based, staged workflows and hindering clinical accountability. Complementarily, expert visual grounding models can accurately localize regions of interest (ROIs), providing explicit, reliable evidence that improves both reasoning accuracy and trust. In this paper, we introduce CARE, advancing Clinical Accountability in multi-modal medical Reasoning with an Evidence-grounded agentic framework. Unlike existing approaches that couple grounding and reasoning within a single generalist model, CARE decomposes the task into coordinated sub-modules to reduce shortcut learning and hallucination: a compact VLM proposes relevant medical entities; an expert entity-referring segmentation model produces pixel-level ROI evidence; and a grounded VLM reasons over the full image augmented by ROI hints. The VLMs are optimized with reinforcement learning with verifiable rewards to align answers with supporting evidence. Furthermore, a VLM coordinator plans tool invocation and reviews evidence-answer consistency, providing agentic control and final verification. Evaluated on standard medical VQA benchmarks, our CARE-Flow (coordinator-free) improves average accuracy by 10.9% over the same size (10B) state-of-the-art (SOTA). With dynamic planning and answer review, our CARE-Coord yields a further gain, outperforming the heavily pre-trained SOTA by 5.2%. Our experiments demonstrate that an agentic framework that emulates clinical workflows, incorporating decoupled specialized models and explicit evidence, yields more accurate and accountable medical AI. Project page: https://xypb.github.io/CARE-Project-Page/
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。
