arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.09909cs.AI
收藏

MedMASLab:多模态医疗多智能体系统的统一协调框架

MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems

National University of Singapore(新加坡国立大学);University of Science and Technology of China(中国科学技术大学);Fudan University(复旦大学);Zhejiang University(浙江大学);vivo;Stanford University(斯坦福大学)

Yunhang Qian, Xiaobin Hu, Jiaquan Yu, Siyang Xin, Xiaokun Chen, Jiangning Zhang, Peng-Tao Jiang, Jiawei Liu, Hongwei Bran Li

AI总结:

本文提出MedMASLab框架,解决医疗多智能体系统中多模态整合碎片化问题,通过标准化通信协议、自动化评估器和大规模基准测试,揭示领域特定性能差距,为未来自主临床系统建立新基准。

摘要:

尽管多智能体系统(MAS)在复杂临床决策支持中展现出潜力,但该领域仍受制于架构碎片化和缺乏标准化多模态整合的阻碍。当前的医疗MAS研究面临非统一的数据摄入管道、不一致的视觉推理评估以及缺乏跨专科基准测试的问题。为解决这些挑战,我们提出了MedMASLab,一个统一的框架和基准测试平台,用于多模态医疗多智能体系统。MedMASLab引入:(1) 一种标准化的多模态智能体通信协议,能够无缝整合24种医学模态下的11种异构MAS架构。(2) 一个自动化临床推理评估器,一种零样本语义评估范式,通过利用大型视觉语言模型来验证诊断逻辑和视觉基础,克服了词汇字符串匹配的局限性。(3) 到目前为止最全面的基准测试,涵盖11个器官系统和473种疾病,标准化了11个临床基准的数据。我们的系统评估揭示了一个关键的领域特定性能差距:虽然MAS提升了推理深度,但当前架构在转换到专门的医学子领域时表现出显著的脆弱性。我们提供了严格的消融分析和交互机制与成本-性能权衡的分析,为未来的自主临床系统建立了新的技术基准。源代码和数据已公开在:https://github.com/NUS-Project/MedMASLab/

英文摘要:

While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration. Current medical MAS research suffers from non-uniform data ingestion pipelines, inconsistent visual-reasoning evaluation, and a lack of cross-specialty benchmarking. To address these challenges, we present MedMASLab, a unified framework and benchmarking platform for multimodal medical multi-agent systems. MedMASLab introduces: (1) A standardized multimodal agent communication protocol that enables seamless integration of 11 heterogeneous MAS architectures across 24 medical modalities. (2) An automated clinical reasoning evaluator, a zero-shot semantic evaluation paradigm that overcomes the limitations of lexical string-matching by leveraging large vision-language models to verify diagnostic logic and visual grounding. (3) The most extensive benchmark to date, spanning 11 organ systems and 473 diseases, standardizing data from 11 clinical benchmarks. Our systematic evaluation reveals a critical domain-specific performance gap: while MAS improves reasoning depth, current architectures exhibit significant fragility when transitioning between specialized medical sub-domains. We provide a rigorous ablation of interaction mechanisms and cost-performance trade-offs, establishing a new technical baseline for future autonomous clinical systems. The source code and data is publicly available at: https://github.com/NUS-Project/MedMASLab/

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。

↑