TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory

TL;DR

TeamMedAgents introduces a multi-agent framework grounded in teamwork theory that enables small language models to perform efficient, accurate multi-step medical reasoning with lower computational costs.

Contribution

The paper presents a novel multi-agent system based on teamwork theory that significantly improves efficiency and stability of medical reasoning in language models.

Findings

Achieves 1-2 orders of magnitude better Pareto efficiency than prior methods.

Maintains competitive accuracy with substantially lower token costs.

Exhibits lowest cross-dataset variance among multi-agent approaches.

Abstract

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.