DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration
This work addresses the challenge of reliable medical consultation for healthcare applications, though it appears incremental by building on existing LLM and multi-agent methods.
The paper tackled the problem of LLM-based medical consultation by addressing the dual nature of symptom inquiry and disease diagnosis, resulting in a framework that outperforms existing LLM-based approaches and achieves competitive performance with state-of-the-art methods on three real-world datasets.
Large Language Models (LLMs) demonstrate strong generalization and reasoning abilities, making them well-suited for complex decision-making tasks such as medical consultation (MC). However, existing LLM-based methods often fail to capture the dual nature of MC, which entails two distinct sub-tasks: symptom inquiry, a sequential decision-making process, and disease diagnosis, a classification problem. This mismatch often results in ineffective symptom inquiry and unreliable disease diagnosis. To address this, we propose \textbf{DDO}, a novel LLM-based framework that performs \textbf{D}ual-\textbf{D}ecision \textbf{O}ptimization by decoupling the two sub-tasks and optimizing them with distinct objectives through a collaborative multi-agent workflow. Experiments on three real-world MC datasets show that DDO consistently outperforms existing LLM-based approaches and achieves competitive performance with state-of-the-art generation-based methods, demonstrating its effectiveness in the MC task. The code is available at https://github.com/zh-jia/DDO.