Expertise-aware Multi-LLM Recruitment and Collaboration for Medical Decision-Making

TL;DR

This paper introduces EMRC, a framework that dynamically recruits and collaborates with multiple LLMs based on expertise and confidence, significantly improving medical decision-making accuracy over single-model approaches.

Contribution

The paper proposes a novel expertise-aware multi-LLM recruitment and collaboration framework that enhances medical decision-making by dynamically selecting and combining specialized LLMs.

Findings

EMRC outperforms state-of-the-art single- and multi-LLM methods.

Achieves 74.45% accuracy on MMLU-Pro-Health, surpassing GPT-4-0613.

Expertise-aware agent recruitment improves diagnostic reliability.

Abstract

Medical Decision-Making (MDM) is a complex process requiring substantial domain-specific expertise to effectively synthesize heterogeneous and complicated clinical information. While recent advancements in Large Language Models (LLMs) show promise in supporting MDM, single-LLM approaches are limited by their parametric knowledge constraints and static training corpora, failing to robustly integrate the clinical information. To address this challenge, we propose the Expertise-aware Multi-LLM Recruitment and Collaboration (EMRC) framework to enhance the accuracy and reliability of MDM systems. It operates in two stages: (i) expertise-aware agent recruitment and (ii) confidence- and adversarial-driven multi-agent collaboration. Specifically, in the first stage, we use a publicly available corpus to construct an LLM expertise table for capturing expertise-specific strengths of multiple LLMs across medical department categories and query difficulty levels. This table enables the subsequent dynamic selection of the optimal LLMs to act as medical expert agents for each medical query during the inference phase. In the second stage, we employ selected agents to generate responses with self-assessed confidence scores, which are then integrated through the confidence fusion and adversarial validation to improve diagnostic reliability. We evaluate our EMRC framework on three public MDM datasets, where the results demonstrate that our EMRC outperforms state-of-the-art single- and multi-LLM methods, achieving superior diagnostic performance. For instance, on the MMLU-Pro-Health dataset, our EMRC achieves 74.45% accuracy, representing a 2.69% improvement over the best-performing closed-source model GPT- 4-0613, which demonstrates the effectiveness of our expertise-aware agent recruitment strategy and the agent complementarity in leveraging each LLM's specialized capabilities.