MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
2026-03-10 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors identify problems in current medical multi-agent systems, such as inconsistent data use and lack of standard tests. They introduce MedMASLab, a unified framework that standardizes communication among different systems, uses advanced models to better evaluate clinical reasoning, and provides a large benchmark covering many diseases and organ systems. Their tests show that while multi-agent systems can reason deeply, they struggle to work well across different medical specialties. This work sets a foundation for improving automated clinical decision support in the future.
Multi-Agent SystemsMultimodal IntegrationClinical Decision SupportBenchmarkingMedical ImagingVision-Language ModelsSemantic EvaluationDiagnostic LogicHealth InformaticsAutomated Reasoning
Authors
Yunhang Qian, Xiaobin Hu, Jiaquan Yu, Siyang Xin, Xiaokun Chen, Jiangning Zhang, Peng-Tao Jiang, Jiawei Liu, Hongwei Bran Li
Abstract
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/