{"ID":2883827,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08115","arxiv_id":"2508.08115","title":"TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory","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.","short_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...","url_abs":"https://arxiv.org/abs/2508.08115","url_pdf":"https://arxiv.org/pdf/2508.08115v3","authors":"[\"Pranav Pushkar Mishra\",\"Mohammad Arvan\",\"Mohan Zalake\"]","published":"2025-08-11T15:55:06Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}