Saved in:
Bibliographic Details
Main Authors: Qian, Yunhang, Hu, Xiaobin, Yu, Jiaquan, Xin, Siyang, Chen, Xiaokun, Zhang, Jiangning, Jiang, Peng-Tao, Liu, Jiawei, Li, Hongwei Bran
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09909
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910058702438400
author Qian, Yunhang
Hu, Xiaobin
Yu, Jiaquan
Xin, Siyang
Chen, Xiaokun
Zhang, Jiangning
Jiang, Peng-Tao
Liu, Jiawei
Li, Hongwei Bran
author_facet Qian, Yunhang
Hu, Xiaobin
Yu, Jiaquan
Xin, Siyang
Chen, Xiaokun
Zhang, Jiangning
Jiang, Peng-Tao
Liu, Jiawei
Li, Hongwei Bran
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2603_09909
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
Qian, Yunhang
Hu, Xiaobin
Yu, Jiaquan
Xin, Siyang
Chen, Xiaokun
Zhang, Jiangning
Jiang, Peng-Tao
Liu, Jiawei
Li, Hongwei Bran
Artificial Intelligence
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/
title MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2603.09909