ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory

2026-03-27

AI Summary

This work addresses the challenge that current large language models struggle to emulate the nonlinear, hypothesis-driven iterative reasoning employed by human clinicians during diagnosis. To bridge this gap, the authors propose a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) for dynamic orchestration with a dual-memory architecture comprising volatile working memory and static experiential memory. This design enables context-aware reasoning and proactive clinical knowledge retrieval, effectively supporting hypothesis generation, evidence validation, and backtracking. Experimental results demonstrate that the proposed approach significantly outperforms existing single-agent and multi-agent baselines in both diagnostic accuracy and interpretability, achieving state-of-the-art performance.

Abstract

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings from symptoms to diagnoses, failing to capture the iterative, hypothesis-driven reasoning inherent to human clinicians. To bridge this gap, we introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians. Unlike rigid sequential chains, ClinicalAgents employs a dynamic orchestration mechanism modeled as a Monte Carlo Tree Search (MCTS) process. This allows an Orchestrator to iteratively generate hypotheses, actively verify evidence, and trigger backtracking when critical information is missing. Central to this framework is a Dual-Memory architecture: a mutable Working Memory that maintains the evolving patient state for context-aware reasoning, and a static Experience Memory that retrieves clinical guidelines and historical cases via an active feedback loop. Extensive experiments demonstrate that ClinicalAgents achieves state-of-the-art performance, significantly enhancing both diagnostic accuracy and explainability compared to strong single-agent and multi-agent baselines.

Problem

• clinical decision making
• non-linear reasoning
• hypothesis-driven diagnosis
• multi-agent systems
• diagnostic accuracy

Innovation

• Multi-Agent Orchestration
• Monte Carlo Tree Search
• Dual-Memory Architecture
• Clinical Decision Making
• Explainable AI