UCAgents: 视觉证据锚定的多智能体医学决策收敛
UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making
AI总结：
UCAgents通过结构化证据审计和单向收敛机制，在医疗视觉问答中提升准确率并降低计算成本，平衡视觉证据揭示与文本干扰避免。
摘要：
视觉语言模型（VLMs）在医疗诊断中展现出潜力，但存在推理脱离的问题，即语言流畅的解释偏离可验证的图像证据，损害临床信任。最近的多智能体框架通过模拟多学科团队（MDT）辩论来缓解单模型偏差，但开放性讨论会放大文本噪声和计算成本，同时无法将推理锚定在视觉证据上，这是医学决策的核心。我们提出UCAgents，一种分层多智能体框架，通过结构化证据审计强制单向收敛。受临床流程启发，UCAgents禁止位置变化，并限制智能体交互到目标证据验证，抑制修辞漂移同时增强视觉信号提取。在UCAgents中引入了一轮询问讨论以揭示潜在的视觉-文本不一致风险。该设计共同约束视觉模糊和文本噪声，我们通过信息论正式化了这一双噪声瓶颈。在四个医疗VQA基准测试中，UCAgents在PathVQA上达到71.3%的准确率（比最新成果高6.0%），同时计算成本降低87.7%。这些结果进一步证实，UCAgents在揭示更多视觉证据和避免混淆文本干扰之间取得了平衡。这些结果表明，UCAgents在诊断可靠性和计算效率方面都适合实际临床部署。代码可在https://github.com/fqhank/UCAgents上获取。
英文摘要：
Vision-Language Models (VLMs) show promise in medical diagnosis, yet suffer from reasoning detachment, where linguistically fluent explanations drift from verifiable image evidence, undermining clinical trust. Recent multi-agent frameworks simulate Multidisciplinary Team (MDT) debates to mitigate single-model bias, but open-ended discussions amplify textual noise and computational cost while failing to anchor reasoning to visual evidence, the cornerstone of medical decision-making. We propose UCAgents, a hierarchical multi-agent framework enforcing unidirectional convergence through structured evidence auditing. Inspired by clinical workflows, UCAgents forbids position changes and limits agent interactions to targeted evidence verification, suppressing rhetorical drift while amplifying visual signal extraction. In UCAgents, a one-round inquiry discussion is introduced to uncover potential risks of visual-textual misalignment. This design jointly constrains visual ambiguity and textual noise, a dual-noise bottleneck that we formalize via information theory. Extensive experiments on four medical VQA benchmarks show UCAgents achieves superior accuracy (71.3% on PathVQA, +6.0% over state-of-the-art) with 87.7% lower token cost, the evaluation results further confirm that UCAgents strikes a balance between uncovering more visual evidence and avoiding confusing textual interference. These results demonstrate that UCAgents exhibits both diagnostic reliability and computational efficiency critical for real-world clinical deployment. Code is available at https://github.com/fqhank/UCAgents.
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。
