HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research

TL;DR

HealthFlow is a novel self-evolving AI agent designed for autonomous healthcare research, capable of refining its strategies through meta planning and learning from scientific literature, significantly advancing AI's role in scientific discovery.

Contribution

The paper introduces HealthFlow, a self-evolving AI agent with a meta-level evolution mechanism and a new benchmark, EHRFlowBench, for complex health data analysis tasks.

Findings

HealthFlow outperforms existing AI frameworks in healthcare research tasks.

Self-evolution enables continuous improvement in problem-solving strategies.

The approach facilitates autonomous learning from scientific literature.

Abstract

The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current AI agents, however, are constrained by static, predefined strategies, limiting their ability to navigate the complex, evolving ecosystem of scientific research. This paper introduces HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its high-level problem-solving policies by distilling procedural successes and failures into a durable, structured knowledge base, enabling it to learn not just how to use tools, but how to strategize. To anchor our research and provide a community resource, we introduce EHRFlowBench, a new benchmark featuring complex health data analysis tasks systematically derived from peer-reviewed scientific literature. Our experiments demonstrate that HealthFlow's self-evolving approach significantly outperforms state-of-the-art agent frameworks. This work offers a new paradigm for intelligent systems that can learn to operationalize the procedural knowledge embedded in scientific content, marking a critical step toward more autonomous and effective AI for healthcare scientific discovery.