Not Just One Agent: Multi-Agent Systems for Medicine from Answer Generation to Accountable Workflow Orchestration
Abstract
Large language models (LLMs) have advanced medical reasoning, but static question-answering performance remains insufficient for clinical workflows that require evolving patient-state tracking, evidence integration, role coordination, and accountable decisions. Medical multi-agent systems (MAS) shift AI from isolated answer generation toward workflow-level clinical intelligence by combining role specialization, memory, tool use, retrieval, communication, and orchestration. This Review maps medical MAS across diagnosis, treatment decision support, imaging, monitoring, surgery, hospital workflow automation, evidence synthesis, medical education, and safety governance. We further synthesize key architectures for collaboration, knowledge-augmented evidence chains, multimodal integration, privacy-preserving coordination, and adaptive optimization, together with evaluation strategies spanning outcomes, process quality, robustness, efficiency, human comparison, and temporal backtesting. We argue that MAS should be validated not merely as answer engines, but as auditable, controllable workflow systems. Future work should prioritize traceable evidence chains, human oversight, privacy-preserving collaboration, standardized reporting, and prospective clinical validation.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.