Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

对齐临床需求与人工智能能力：大语言模型医学推理综述

Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care. This survey examines recent progress in medical LLMs, focusing on reasoning applications and requirements. 大语言模型（LLMs）已成为医疗保健领域的重要工具，在临床推理和患者护理方面展现出日益增长的潜力。本综述探讨了医学大语言模型的最新进展，重点关注推理应用与需求。

We present a dual-view approach that connects clinical practice with computational methods. On the clinical side, we establish a five-level competency scheme following Miller’s Pyramid, progressing from knowledge recall to dynamic case management. 我们提出了一种连接临床实践与计算方法的双重视角。在临床方面，我们遵循米勒金字塔（Miller’s Pyramid）建立了一个五级能力方案，从知识回忆逐步进阶到动态病例管理。

On the computational side, we link deductive, inductive, and abductive reasoning patterns to common medical goals and tasks. We also introduce a benchmark dataset spanning five levels of medical reasoning capability and report results on 18 state-of-the-art models, revealing that medical specialist models excel in diagnosis-centric tasks while general models lead in decision support and dialogue. 在计算方面，我们将演绎、归纳和溯因推理模式与常见的医学目标和任务联系起来。我们还引入了一个涵盖五个医学推理能力层级的基准数据集，并报告了 18 个最先进模型的测试结果，揭示了医学专业模型在以诊断为中心的任务中表现优异，而通用模型在决策支持和对话方面处于领先地位。

We conclude by discussing current progress and open challenges, including data limitations, hallucination, and grounding issues, and outline directions toward safer, more reliable, and workflow-ready systems. 最后，我们讨论了当前的进展和面临的挑战，包括数据局限性、幻觉和基础性问题，并概述了迈向更安全、更可靠且可投入工作流的系统的发展方向。