XrayClaw：协作-竞争多智能体对齐用于可信的胸部X光诊断
XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis
- Shenzhen University of Advanced Technology, Shenzhen, China（深圳理工大学，深圳，中国）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出XrayClaw框架，通过协作-竞争架构提升胸部X光诊断的可靠性，实现高准确性和临床推理一致性。
AI中文摘要：
胸部X光解读是一项基础且复杂的临床任务，日益依赖人工智能自动化。然而，传统单体模型缺乏必要的细致推理能力，常导致逻辑不一致和诊断幻觉。多智能体系统通过模拟协作咨询提供潜在解决方案，但现有框架在单一基础模型下仍易产生共识误差。本文引入XrayClaw，一种新型框架，通过复杂的协作-竞争架构实现多智能体对齐。XrayClaw整合四个专门协作智能体以模拟系统临床工作流程，同时配备一个竞争智能体作为独立审计者。为协调这些不同的诊断路径，我们提出竞争偏好优化，通过惩罚不合理的推理来强制分析与整体解读之间的相互验证。在MS-CXR-T、MIMIC-CXR和CheXbench基准上的广泛实证评估表明，XrayClaw在诊断准确性、临床推理一致性和零样本领域泛化方面均达到最先进的水平。我们的结果表明，XrayClaw有效缓解了累积幻觉并提高了自动X光诊断的整体可靠性，建立了可信医学影像分析的新范式。
英文摘要：
Chest X-ray (CXR) interpretation is a fundamental yet complex clinical task that increasingly relies on artificial intelligence for automation. However, traditional monolithic models often lack the nuanced reasoning required for trustworthy diagnosis, frequently leading to logical inconsistencies and diagnostic hallucinations. While multi-agent systems offer a potential solution by simulating collaborative consultations, existing frameworks remain susceptible to consensus-based errors when instantiated by a single underlying model. This paper introduces XrayClaw, a novel framework that operationalizes multi-agent alignment through a sophisticated cooperative-competitive architecture. XrayClaw integrates four specialized cooperative agents to simulate a systematic clinical workflow, alongside a competitive agent that serves as an independent auditor. To reconcile these distinct diagnostic pathways, we propose Competitive Preference Optimization, a learning objective that penalizes illogical reasoning by enforcing mutual verification between analytical and holistic interpretations. Extensive empirical evaluations on the MS-CXR-T, MIMIC-CXR, and CheXbench benchmarks demonstrate that XrayClaw achieves state-of-the-art performance in diagnostic accuracy, clinical reasoning fidelity, and zero-shot domain generalization. Our results indicate that XrayClaw effectively mitigates cumulative hallucinations and enhances the overall reliability of automated CXR diagnosis, establishing a new paradigm for trustworthy medical imaging analysis.
