{"ID":2887061,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02621","arxiv_id":"2508.02621","title":"HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research","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.","short_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 nav...","url_abs":"https://arxiv.org/abs/2508.02621","url_pdf":"https://arxiv.org/pdf/2508.02621v2","authors":"[\"Yinghao Zhu\",\"Yifan Qi\",\"Zixiang Wang\",\"Lei Gu\",\"Dehao Sui\",\"Haoran Hu\",\"Xichen Zhang\",\"Ziyi He\",\"Junjun He\",\"Liantao Ma\",\"Lequan Yu\"]","published":"2025-08-04T17:08:47Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.LG\",\"cs.MA\"]","methods":"[]","has_code":false}