Learning to Be A Doctor: Searching for Effective Medical Agent Architectures

• URL: http://arxiv.org/abs/2504.11301v1
• Date: Tue, 15 Apr 2025 15:44:21 GMT
• Title: Learning to Be A Doctor: Searching for Effective Medical Agent Architectures
• Authors: Yangyang Zhuang, Wenjia Jiang, Jiayu Zhang, Ze Yang, Joey Tianyi Zhou, Chi Zhang,
• Abstract summary: This paper introduces a novel framework for the automated design of medical agent architectures.<n>Motivated by the success of automated machine learning (AutoML), we define a hierarchical and expressive agent search space.<n>Our framework conceptualizes medical agents as graph-based architectures composed of diverse, functional node types.
• Score: 32.82784216021035
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM)-based agents have demonstrated strong capabilities across a wide range of tasks, and their application in the medical domain holds particular promise due to the demand for high generalizability and reliance on interdisciplinary knowledge. However, existing medical agent systems often rely on static, manually crafted workflows that lack the flexibility to accommodate diverse diagnostic requirements and adapt to emerging clinical scenarios. Motivated by the success of automated machine learning (AutoML), this paper introduces a novel framework for the automated design of medical agent architectures. Specifically, we define a hierarchical and expressive agent search space that enables dynamic workflow adaptation through structured modifications at the node, structural, and framework levels. Our framework conceptualizes medical agents as graph-based architectures composed of diverse, functional node types and supports iterative self-improvement guided by diagnostic feedback. Experimental results on skin disease diagnosis tasks demonstrate that the proposed method effectively evolves workflow structures and significantly enhances diagnostic accuracy over time. This work represents the first fully automated framework for medical agent architecture design and offers a scalable, adaptable foundation for deploying intelligent agents in real-world clinical environments.

Related papers

• Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions [16.50490537786593]
  We introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents. Unlike prior approaches, our framework requires doctor agents to actively engage with patients through multi-turn conversations. We incorporate self improvement mechanisms that allow models to iteratively refine their diagnostic strategies.
  arXiv  Detail & Related papers  (2025-03-28T17:59:53Z)
• Large Language Model Agent: A Survey on Methodology, Applications and Challenges [88.3032929492409]
  Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence.<n>This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy.<n>Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time.
  arXiv  Detail & Related papers  (2025-03-27T12:50:17Z)
• Empowering Medical Multi-Agents with Clinical Consultation Flow for Dynamic Diagnosis [20.59719567178192]
  We propose a multi-agent framework inspired by consultation flow and reinforcement learning (RL) to simulate the entire consultation process. Our approach incorporates a hierarchical action set, structured from clinic consultation flow and medical textbook, to effectively guide the decision-making process. This strategy improves agent interactions, enabling them to adapt and optimize actions based on the dynamic state.
  arXiv  Detail & Related papers  (2025-03-19T08:47:18Z)
• KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis [6.001401133840334]
  KG4Diagnosis is a novel hierarchical multi-agent framework that combines Large Language Models with automated knowledge graph construction.<n>Our framework mirrors real-world medical systems through a two-tier architecture: a general practitioner (GP) agent for initial assessment and triage, coordinating with specialized agents for in-depth diagnosis in specific domains.
  arXiv  Detail & Related papers  (2024-12-22T02:40:59Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice through Interactive Sequential Benchmarking [58.25862290294702]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow.<n>We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios [46.729092855387165]
  We study the choice of the backbone LLM for medical AI agents, which is the foundation for the agent's overall reasoning and action generation.<n>Our findings demonstrate o1's ability to enhance diagnostic accuracy and consistency, paving the way for smarter, more responsive AI tools.
  arXiv  Detail & Related papers  (2024-11-16T18:19:53Z)
• Demystifying Large Language Models for Medicine: A Primer [50.83806796466396]
  Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare. This tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice.
  arXiv  Detail & Related papers  (2024-10-24T15:41:56Z)
• Adaptive Reasoning and Acting in Medical Language Agents [3.8936716676293917]
  This paper presents an innovative large language model (LLM) agent framework for enhancing diagnostic accuracy in simulated clinical environments. The proposed automatic correction enables doctor agents to iteratively refine their reasoning and actions following incorrect diagnoses.
  arXiv  Detail & Related papers  (2024-10-13T21:45:16Z)
• A process algebraic framework for multi-agent dynamic epistemic systems [55.2480439325792]
  We propose a unifying framework for modeling and analyzing multi-agent, knowledge-based, dynamic systems. On the modeling side, we propose a process algebraic, agent-oriented specification language that makes such a framework easy to use for practical purposes.
  arXiv  Detail & Related papers  (2024-07-24T08:35:50Z)
• Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining [121.89793208683625]
  Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks. We propose a new paradigm called Medical-knedge-enhanced mulTimOdal pretRaining (MOTOR)
  arXiv  Detail & Related papers  (2023-04-26T01:26:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.