While reinforcement learning for large language model alignment has progressed rapidly in recent years, transferring these paradigms to high-stakes medical question answering reveals a fundamental paradigm mismatch. Reinforcement Learning from Human Feedback relies on preference annotations that are prohibitively expensive and often fail to reflect the absolute correctness of medical facts. Reinforcement Learning from Verifiable Rewards lacks effective automatic verifiers and struggles to handle complex clinical contexts. Meanwhile, medical alignment requires the simultaneous optimization of correctness, safety, and compliance, yet multi-objective heterogeneous reward signals are prone to scale mismatch and optimization conflicts. To address these challenges, we propose a robust medical alignment paradigm. We first construct a holistic multi-dimensional medical alignment matrix that decomposes alignment objectives into four categories: fundamental capabilities, expert knowledge, online feedback, and format specifications. Within each category, we establish a closed loop of where observable metrics inform attributable diagnosis, which in turn drives optimizable rewards, thereby providing fine-grained, high-resolution supervision signals for subsequent iterative optimization. To resolve gradient domination and optimization instability problem caused by heterogeneous signals, we further propose a unified optimization mechanism. This mechanism employs Reference-Frozen Normalization to align reward scales and implements a Tri-Factor Adaptive Dynamic Weighting strategy to achieve collaborative optimization that is weakness-oriented, risk-prioritized, and redundancy-reducing. Experimental results demonstrate the effectiveness of our proposed paradigm in real-world medical scenario evaluations, establishing a new paradigm for complex alignment in vertical domains.
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
DAMO Academy, Alibaba Group(达摩院,阿里巴巴集团);Hupan Laboratory(湖畔实验室);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Department of Radiology, The Affiliated Yangming Hospital of Ningbo University(宁波大学附属阳明医院放射科);Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University(浙江大学伊利诺伊大学厄巴纳香槟校区联合学院,浙江大学);Hepato-Pancreato-Biliary Center, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua Medicine, Tsinghua University(清华长庚医院肝胆胰中心,清华大学临床医学院,清华医学,清华大学);School of Software, Tsinghua University(清华大学软件学院);Beijing National Research Center for Information Science and Technology, Tsinghua University(清华大学北京信息科学与技术国家研究中心)
Artificial General Intelligence for Medical Imaging Analysis
Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);The University of Texas at Arlington(德克萨斯大学阿灵顿分校);The University of Georgia(佐治亚大学);Beijing Jiaotong University(北京交通大学);Chinese University of Hong Kong(香港中文大学);Second Xiangya Hospital(湘雅二医院)
An Evolutionary Agentic Approach for Open-ended Image Quality Perception
New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);The Hong Kong University of Science and Technology(香港科技大学);Transsion(传音)
Reasoning LLMs in the Medical Domain: A Literature Survey
Fraunhofer IAIS - Department of Media Engineering(弗劳恩霍夫研究所媒体工程部门);University of Bonn - Department of Computer Science(波恩大学计算机科学系);West-AI - Federal Ministry of Education and Research(西德人工智能 - 教育与研究部)
MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks
Stanford University School of Medicine(斯坦福大学医学院);Stanford Health Care(斯坦福健康系统);Center for Research on Foundation Models (CRFM) & Department of Computer Science(基础模型研究中心(CRFM)及计算机科学系);Microsoft Corporation(微软公司);Stanford Institute for Human-Centered AI(斯坦福大学人本人工智能研究所)
Holistic Evaluation of GPT-4V for Biomedical Imaging
University of Georgia(佐治亚大学);Beijing Jiaotong University(北京交通大学);Northwestern Polytechnical University(西北工业大学);University of Texas at Arlington(德克萨斯大学阿灵顿分校);University of Electronic Science and Technology of China(电子科技大学)
SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction
Stockholm University(斯德哥尔摩大学);Skatturinn (Iceland Revenue and Customs)(冰岛税务总局(冰岛税收和海关局))
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
FAIR at Meta(Meta FAIR研究院);Hôpital Cochin, AP-HP.Centre Université Paris Cité(科钦医院、巴黎大学中心公共医疗援助系统);Université Paris Cité(巴黎大学);CentraleSupélec, Université Paris-Saclay(巴黎萨克雷大学中央理工学院)
MAIA: A Collaborative Medical AI Platform for Integrated Healthcare Innovation
Department of Biomedical Engineering and Health Systems, KTH, Royal Institute of Technology(生物医学工程与健康系统系,皇家理工学院);Department of Clinical Sciences, Intervention and Engineering, Karolinska Institutet(临床科学、干预与工程系,卡罗林斯卡研究所);Division of Medical Radiation Physics, Department of Physics, Stockholm University(医学放射物理 division,物理系,斯德哥尔摩大学);Department of Oncology-Pathology, Karolinska Institutet(肿瘤学-病理学系,卡罗林斯卡研究所);Department of Radiology, Karolinska University Hospital(放射学系,卡罗林斯卡大学医院);Department of Molecular Medicine and Surgery, Karolinska Institutet(分子医学与外科系,卡罗林斯卡研究所);Department of Neurobiology, Care Sciences and Society, Karolinska Institutet(神经生物学、护理科学与社会系,卡罗林斯卡研究所)
本文提出开源协作平台 MAIA,基于 Kubernetes 集成数据、建模、标注、部署与临床反馈工具,以推动医学影像 AI 从研究到临床的可复现转化。
MAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation
Anhui University(安徽大学);The First Affiliated Hospital of Anhui Medical University(安徽医科大学第一附属医院);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Peng Cheng Laboratory(鹏城实验室)
Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team
American International University-Bangladesh(美国国际大学-孟加拉国);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Cornell University(康奈尔大学);Qatar Computing Research Institute(卡塔尔计算研究所)
Auditing medical multi-agent AI reveals risks of false consensus
National Engineering Research Center for Software Engineering, Peking University(北京大学软件工程国家工程研究中心);School of Computing and Data Science, The University of Hong Kong(香港大学计算机与数据科学学院);Department of Nephrology, Peking University Third Hospital(北京大学第三医院肾内科);Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Lymphoma, Peking University Cancer Hospital & Institute(教育部癌症发生与转化研究重点实验室、北京大学肿瘤医院淋巴瘤科);Department of Automation, Tsinghua University(清华大学自动化系);Centre for Medical Informatics, The University of Edinburgh(爱丁堡大学医学信息学中心);Health Data Research UK(英国健康数据研究机构);Lee Kong Chian School of Medicine, Nanyang Technological University(南洋理工大学李科贤医学院);State Key Laboratory for Novel Software Technology, School of Computer Science, Nanjing University(南京大学新型软件技术国家重点实验室、计算机科学学院)