HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
This work addresses the problem of static AI agents in healthcare research, offering a new paradigm for more autonomous and effective scientific discovery, though it appears incremental in its application to a specific domain.
The paper tackles the challenge of transforming vast scientific knowledge into an active engine for discovery in healthcare by introducing HealthFlow, a self-evolving AI agent that autonomously refines its problem-solving policies, and it significantly outperforms state-of-the-art agent frameworks in experiments.
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.