Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Tree

TL;DR

This paper introduces Tree-of-Reasoning, a multi-agent framework with a tree structure for improved complex medical diagnosis by enhancing reasoning depth and evidence tracking in large language models.

Contribution

The paper presents a novel multi-agent reasoning framework with a tree structure and cross-validation mechanism to improve medical diagnosis accuracy in complex scenarios.

Findings

Outperforms baseline methods on real-world medical data

Enhances reasoning depth and evidence tracking in LLMs

Improves diagnostic accuracy in complex cases

Abstract

Large language models (LLMs) have shown great potential in the medical domain. However, existing models still fall short when faced with complex medical diagnosis task in the real world. This is mainly because they lack sufficient reasoning depth, which leads to information loss or logical jumps when processing a large amount of specialized medical data, leading to diagnostic errors. To address these challenges, we propose Tree-of-Reasoning (ToR), a novel multi-agent framework designed to handle complex scenarios. Specifically, ToR introduces a tree structure that can clearly record the reasoning path of LLMs and the corresponding clinical evidence. At the same time, we propose a cross-validation mechanism to ensure the consistency of multi-agent decision-making, thereby improving the clinical reasoning ability of multi-agents in complex medical scenarios. Experimental results on real-world medical data show that our framework can achieve better performance than existing baseline methods.