ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Huiya, Zhu, Yinghao, Wang, Zixiang, Wang, Yasha, Gao, Junyi, Ma, Liantao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909726806114304
author Zhao, Huiya
Zhu, Yinghao
Wang, Zixiang
Wang, Yasha
Gao, Junyi
Ma, Liantao
author_facet Zhao, Huiya
Zhu, Yinghao
Wang, Zixiang
Wang, Yasha
Gao, Junyi
Ma, Liantao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis
Zhao, Huiya
Zhu, Yinghao
Wang, Zixiang
Wang, Yasha
Gao, Junyi
Ma, Liantao
Artificial Intelligence
Computation and Language
Multiagent Systems
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.
title ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis
topic Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2508.04915