ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 6 Aug 2025.
Builds on
18 of 27 references.
References · 18
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
- 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
- 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
- 2024To Believe or Not to Believe Your LLMcited by 120
- 2024AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulatorcited by 101
- 2024Large language model validity via enhanced conformal prediction methodscited by 92
- 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
- 2024Can Unconfident LLM Annotations Be Used for Confident Conclusions?cited by 49
- 2024BioRAG: A RAG-LLM Framework for Biological Question Reasoningcited by 43
6 more
- 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworkscited by 40
- 2024LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentationcited by 23
- 2024ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaborationcited by 23
- 2024ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemescited by 13
- 2024Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertaintycited by 11
- 2024LLM Confidence Evaluation Measures in Zero-Shot CSS Classificationcited by 6
Built on by
Citing papers per year: 2026: 2.
2 papers.