用团队协作理论让小模型高效完成复杂诊疗推理。
TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory
- 基于团队协作理论构建多智能体协同机制
- 在8个医学基准上实现精度高、耗 token 量低
- 适合资源有限的临床场景部署
复杂医疗推理长期依赖前沿大语言模型才能达到临床可接受的准确率，造成计算成本高昂，限制了在资源受限临床环境中的应用。我们提出 TeamMedAgents，一个模块化多智能体框架，将 Salas 等人的循证团队协作理论转化为计算机制——共享心智模型、团队领导力、团队导向、信任网络和相互监控，使小型语言模型能够高效完成多步临床推理。在8个医学基准上的评估显示，TeamMedAgents 将帕累托效率前沿提升了1-2个数量级，在显著低于 MDAgents、MedAgents、DyLAN 和 ReConcile 的 token 消耗下仍保持竞争力。该框架在多数据集上表现出最低的方差，无需针对任务微调即可部署。结果表明，基于理论的协调机制为在资源受限环境中部署高效医疗 AI 提供了关键支撑。
原文摘要 · Abstract (English)
Complex medical reasoning has historically required frontier language models to achieve clinically-acceptable accuracy, creating computational barriers that limit deployment in resource-constrained clinical settings. We present TeamMedAgents, a modular multi-agent framework that translates Salas et al.'s evidence-based teamwork theory into computational mechanisms--shared mental models, team leadership, team orientation, trust networks, and mutual monitoring--enabling Small Language Models to perform multi-step clinical reasoning efficiently. Evaluation across 8 medical benchmarks demonstrates that TeamMedAgents advances the Pareto efficiency frontier by 1-2 orders of magnitude, achieving competitive accuracy at substantially lower token cost than MDAgents, MedAgents, DyLAN, and ReConcile. The framework exhibits the lowest cross-dataset variance among multi-agent approaches, enabling deployment without per-task tuning. Our results establish that theory-grounded coordination mechanisms provide essential scaffolding for deploying efficient medical AI in resource-constrained clinical environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。