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

TL;DR

ClinicalAgents introduces a multi-agent framework with dual-memory and Monte Carlo Tree Search to improve clinical diagnosis accuracy and explainability over traditional static models.

Contribution

The paper presents a novel multi-agent system with dual-memory architecture and dynamic orchestration for improved clinical decision-making.

Findings

Achieves state-of-the-art diagnostic accuracy.

Enhances explainability of clinical reasoning.

Outperforms existing single-agent and multi-agent baselines.

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.