Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zhuohan Ge, Haoyang Li, Yubo Wang, Nicole Hu, Chen Jason Zhang, Qing Li

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.

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

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.

Paper Structure

This paper contains 24 sections, 15 equations, 1 figure, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. LLMs in Clinical Decision-Making (CDM)
  4. Multi-Agent Systems in CDM
  5. Methodology
  6. Framework Overview
  7. Clinical Orchestrator
  8. Dual-Memory System
  9. Working Memory
  10. Experience Memory
  11. Experiments
  12. Experimental Settings
  13. Datasets and Evaluation Metrics
  14. MedChain (Benchmark).
  15. Baselines
  16. ...and 9 more sections

Figures (1)

  • Figure 1: Overview of the ClinicalAgents framework. A Clinical Orchestrator coordinates a pool of specialized agents and a dual-memory system (working memory and experience memory) to execute an iterative Perceive--Hypothesize--Verify--Update loop with evidence-triggered backtracking.

Theorems & Definitions (1)

  • definition 1: The Memory-based MCTS Problem