A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making

2025-09-18

AI Summary

Medical decision-making often requires integrating cross-specialty knowledge, yet existing LLM-based multi-agent frameworks rely on static role assignment, limiting adaptability to dynamic diagnostic needs. To address this, we propose a knowledge-driven adaptive multi-agent collaboration framework that dynamically generates agent roles in real time by detecting knowledge gaps, thereby enabling on-demand formation and expansion of expert agent teams. Our approach integrates three core components: knowledge-gap detection, context-aware reasoning, and iterative discussion synthesis—collectively supporting diagnosis-driven collaborative inference. Evaluated on realistic medical benchmarks, our method significantly outperforms both single-agent baselines and conventional multi-agent approaches, particularly on interdisciplinary, high-complexity tasks such as cancer prognosis prediction. These results empirically validate the efficacy of dynamic knowledge integration in enhancing clinical decision-making capabilities.

Technology Category

• Multiagent Systems: Teamwork
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Medical decision-making often involves integrating knowledge from multiple clinical specialties, typically achieved through multidisciplinary teams. Inspired by this collaborative process, recent work has leveraged large language models (LLMs) in multi-agent collaboration frameworks to emulate expert teamwork. While these approaches improve reasoning through agent interaction, they are limited by static, pre-assigned roles, which hinder adaptability and dynamic knowledge integration. To address these limitations, we propose KAMAC, a Knowledge-driven Adaptive Multi-Agent Collaboration framework that enables LLM agents to dynamically form and expand expert teams based on the evolving diagnostic context. KAMAC begins with one or more expert agents and then conducts a knowledge-driven discussion to identify and fill knowledge gaps by recruiting additional specialists as needed. This supports flexible, scalable collaboration in complex clinical scenarios, with decisions finalized through reviewing updated agent comments. Experiments on two real-world medical benchmarks demonstrate that KAMAC significantly outperforms both single-agent and advanced multi-agent methods, particularly in complex clinical scenarios (i.e., cancer prognosis) requiring dynamic, cross-specialty expertise. Our code is publicly available at: https://github.com/XiaoXiao-Woo/KAMAC.

Problem

• Dynamic knowledge integration in medical decision-making
• Overcoming static role limitations in multi-agent LLM collaboration
• Adaptive expert team formation for complex clinical scenarios

Innovation

• Dynamic expert team formation based on context
• Knowledge-driven gap identification and specialist recruitment
• Adaptive multi-agent collaboration for medical decisions