Saved in:
Bibliographic Details
Main Authors: Mishra, Pranav Pushkar, Arvan, Mohammad, Zalake, Mohan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.08115
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915900413706240
author Mishra, Pranav Pushkar
Arvan, Mohammad
Zalake, Mohan
author_facet Mishra, Pranav Pushkar
Arvan, Mohammad
Zalake, Mohan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08115
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory
Mishra, Pranav Pushkar
Arvan, Mohammad
Zalake, Mohan
Artificial Intelligence
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.
title TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory
topic Artificial Intelligence
url https://arxiv.org/abs/2508.08115