DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making

TL;DR

DynamiCare introduces a multi-agent framework that models iterative, interactive medical decision-making, reflecting real-world diagnostic processes more accurately than previous single-turn models, and provides a new benchmark for such systems.

Contribution

It presents DynamiCare, a novel multi-agent framework for dynamic, interactive medical diagnosis, and introduces MIMIC-Patient, a dataset supporting patient-level simulations.

Findings

Demonstrates the feasibility of multi-round, interactive diagnosis with LLM agents.

Establishes the first benchmark for dynamic clinical decision-making.

Shows improved realism over single-turn diagnostic models.

Abstract

The rise of Large Language Models (LLMs) has enabled the development of specialized AI agents with domain-specific reasoning and interaction capabilities, particularly in healthcare. While recent frameworks simulate medical decision-making, they largely focus on single-turn tasks where a doctor agent receives full case information upfront -- diverging from the real-world diagnostic process, which is inherently uncertain, interactive, and iterative. In this paper, we introduce MIMIC-Patient, a structured dataset built from the MIMIC-III electronic health records (EHRs), designed to support dynamic, patient-level simulations. Building on this, we propose DynamiCare, a novel dynamic multi-agent framework that models clinical diagnosis as a multi-round, interactive loop, where a team of specialist agents iteratively queries the patient system, integrates new information, and dynamically adapts its composition and strategy. We demonstrate the feasibility and effectiveness of DynamiCare through extensive experiments, establishing the first benchmark for dynamic clinical decision-making with LLM-powered agents.