{"ID":2886025,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04915","arxiv_id":"2508.04915","title":"ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis","abstract":"The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better strategic planners, a crucial skill for complex domains like healthcare. We introduce HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its own high-level problem-solving policies by distilling procedural successes and failures into a durable, strategic knowledge base. To anchor our research and facilitate reproducible evaluation, we introduce EHRFlowBench, a new benchmark featuring complex, realistic health data analysis tasks derived from peer-reviewed clinical research. Our comprehensive experiments demonstrate that HealthFlow's self-evolving approach significantly outperforms state-of-the-art agent frameworks. This work marks a necessary shift from building better tool-users to designing smarter, self-evolving task-managers, paving the way for more autonomous and effective AI for scientific discovery.","short_abstract":"The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better strategic planners, a crucial skill for complex domains like healthcare. We introduce HealthFlow, a s...","url_abs":"https://arxiv.org/abs/2508.04915","url_pdf":"https://arxiv.org/pdf/2508.04915v1","authors":"[\"Huiya Zhao\",\"Yinghao Zhu\",\"Zixiang Wang\",\"Yasha Wang\",\"Junyi Gao\",\"Liantao Ma\"]","published":"2025-08-06T22:39:38Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.MA\"]","methods":"[]","has_code":false}