Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913969815420928 |
|---|---|
| author | Wang, Wenxuan Ma, Zizhan Ding, Meidan Zheng, Shiyi Liu, Shengyuan Liu, Jie Ji, Jiaming Chen, Wenting Li, Xiang Shen, Linlin Yuan, Yixuan |
| author_facet | Wang, Wenxuan Ma, Zizhan Ding, Meidan Zheng, Shiyi Liu, Shengyuan Liu, Jie Ji, Jiaming Chen, Wenting Li, Xiang Shen, Linlin Yuan, Yixuan |
| contents | The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning) and test-time mechanisms (e.g., prompt engineering, multi-agent systems). We analyze how these techniques are applied across different data modalities (text, image, code) and in key clinical applications such as diagnosis, education, and treatment planning. Furthermore, we survey the evolution of evaluation benchmarks from simple accuracy metrics to sophisticated assessments of reasoning quality and visual interpretability. Based on an analysis of 60 seminal studies from 2022-2025, we conclude by identifying critical challenges, including the faithfulness-plausibility gap and the need for native multimodal reasoning, and outlining future directions toward building efficient, robust, and sociotechnically responsible medical AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00669 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications Wang, Wenxuan Ma, Zizhan Ding, Meidan Zheng, Shiyi Liu, Shengyuan Liu, Jie Ji, Jiaming Chen, Wenting Li, Xiang Shen, Linlin Yuan, Yixuan Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning) and test-time mechanisms (e.g., prompt engineering, multi-agent systems). We analyze how these techniques are applied across different data modalities (text, image, code) and in key clinical applications such as diagnosis, education, and treatment planning. Furthermore, we survey the evolution of evaluation benchmarks from simple accuracy metrics to sophisticated assessments of reasoning quality and visual interpretability. Based on an analysis of 60 seminal studies from 2022-2025, we conclude by identifying critical challenges, including the faithfulness-plausibility gap and the need for native multimodal reasoning, and outlining future directions toward building efficient, robust, and sociotechnically responsible medical AI. |
| title | Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.00669 |