Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely almost entirely on frontier models (e.g., GPT), whose API-based deployment incurs high cost, high latency, and privacy risks that conflict with on-premise clinical requirements. We present Meissa, a lightweight 4B-parameter medical MM-LLM that brings agentic capability offline. Instead of imitating static answers, Meissa learns both when to engage external interaction (strategy selection) and how to execute multi-step interaction (strategy execution) by distilling structured trajectories from frontier models. Specifically, we propose: (1) Unified trajectory modeling: trajectories (reasoning and action traces) are represented within a single state-action-observation formalism, allowing one model to generalize across heterogeneous medical environments. (2) Three-tier stratified supervision: the model's own errors trigger progressive escalation from direct reasoning to tool-augmented and multi-agent interaction, explicitly learning difficulty-aware strategy selection. (3) Prospective-retrospective supervision: pairing exploratory forward traces with hindsight-rationalized execution traces enables stable learning of effective interaction policies. Trained on 40K curated trajectories, Meissa matches or exceeds proprietary frontier agents in 10 of 16 evaluation settings across 13 medical benchmarks spanning radiology, pathology, and clinical reasoning. Using over 25x fewer parameters than typical frontier models like Gemini-3, Meissa operates fully offline with 22x lower end-to-end latency compared to API-based deployment. Data, models, and environments are released at https://github.com/Schuture/Meissa.
MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow
National University of Singapore(新加坡国立大学);University of Oxford(牛津大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));National University of Defense Technology(国防科技大学);The Second Affiliated Hospital Zhejiang University School of Medicine(浙江大学医学院附属第二医院)
CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
Microsoft Research Asia(微软亚洲研究院);Department of Biomedical Engineering, Yale University(耶鲁大学生物医学工程系);Department of Radiology & Biomedical Imaging, Yale University(耶鲁大学放射学与生物医学成像系)
OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
Shanghai AI Laboratory(上海人工智能实验室);School of Computing, National University of Singapore(新加坡国立大学计算机学院);Shanghai Jiaotong University(上海交通大学);Tsinghua University(清华大学)
OmniPath: A Multi-Modal Agentic Framework for Auditing Wheelchair Accessibility
Causal AI Lab, Department of Information Systems, University of Maryland Baltimore County(因果AI实验室,信息系统系,马里兰大学巴尔的摩分校);Department of Computer Science & Software Engineering, Miami University(计算机科学与软件工程系,迈阿密大学)
PULSE: Agentic Investigation with Passive Sensing for Proactive Affective Intervention in Cancer Survivorship
Department of Systems and Information Engineering, University of Virginia(系统与信息工程系,弗吉尼亚大学);Center for Behavioral Health and Technology, University of Virginia(行为健康与技术中心,弗吉尼亚大学);Department of Computer Science, University of Virginia(计算机科学系,弗吉尼亚大学)
Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Shanghai University of Finance and Economics(上海财经大学);Technische Universität München(慕尼黑技术大学);Southwestern University of Finance and Economics(西南财经大学)
LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA(弗吉尼亚理工大学计算机科学系);Department of Computational Modeling and Data Analytics, Virginia Tech, Blacksburg, VA, USA(弗吉尼亚理工大学计算建模与数据分析系);Institute of Information and Technology, University of Dhaka, Dhaka, Bangladesh(达卡大学信息技术学院);Fralin Biomedical Research Institute at VTC: Cancer Research Center, Washington DC, USA(弗拉林生物医学研究中心:癌症研究中心)
Shanghai Jiaotong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The Chinese University of Hong Kong(香港中文大学);Wuhan University(武汉大学)
SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication Coaching
Quanta People Solutions Pvt. Ltd.(Quant People Solutions私人有限公司);Panorama AI Solutions(全景人工智能解决方案公司);University College of Engineering, Osmania University(奥萨马尼亚大学工程学院)
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
Department of Nuclear Engineering, Texas A\&M University, College Station, TX, USA;College of Performance, Visualization;Fine Arts, Texas A\&M University, College Station, TX, USA
Cognitive Inception: Agentic Reasoning against Visual Deceptions by Injecting Skepticism
CFAR, Agency for Science, Technology and Research (A*STAR), Singapore(科技研究局(A*STAR)认知智能研究所,新加坡);IHPC, Agency for Science, Technology and Research (A*STAR), Singapore(科技研究局(A*STAR)信息处理中心,新加坡);ROSE Lab, School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电子与电气工程学院ROSE实验室)
CANDLE: A Cross-Modal Agentic Knowledge Distillation Framework for Interpretable Sarcopenia Diagnosis
College of Information and Engineering, First Affiliated Hospital, Wenzhou Medical University(温州医科大学附属第一医院信息与工程学院);Wenzhou Institute, University of Chinese Academy of Sciences(中国科学院大学温州研究院);Department of Gastrointestinal Surgery, First Affiliated Hospital, Wenzhou Medical University(温州医科大学附属第一医院胃肠外科)
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能研究院);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);University of Science and Technology Beijing(北京科技大学)
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
Beijing University of Posts and Telecommunications(北京邮电大学);University of Georgia(佐治亚大学);South China University of Technology(华南理工大学);Technical University of Munich, University of Cologne(慕尼黑技术大学、科隆大学);SenseTime Research(商汤科技研究院);Qingyuan Research Institute, Shanghai Jiaotong University(青原研究院,上海交通大学)
MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning
Chinese University of Hong Kong, Hong Kong SAR, China(香港中文大学);Hunyuan Group, Tencent(腾讯洪音集团);Institute of Automation, the Chinese Academy of Sciences, Beijing, China(中国科学院自动化研究所);Dalian University of Technology, Dalian, China(大连理工大学);Stanford University, Stanford, USA(斯坦福大学)
Artificial Intelligence Graduate School, Ulsan National Institute of Science and Engineering(人工智能研究生院,乌山科学与工程研究院);Department of Computer Science and Engineering, Ulsan National Institute of Science and Engineering(计算机科学与工程系,乌山科学与工程研究院)
School of Intelligence Science and Technology, Peking University(北京理工大学智能科学与技术学院);DAMO Academy, Alibaba group(阿里巴巴集团大模型研究院);Hupan Lab(虎扑实验室);National Key Laboratory of General Artificial Intelligence, Peking University(北京人工智能 general artificial intelligence 国家重点实验室);Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系)
DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows
School of Computer Engineering and Science, Shanghai University(上海大学计算机工程与科学学院);School of Foreign Languages, East China Normal University(华东师范大学外国语言学系);School of Foreign Studies, Shanghai University(上海大学外国语言学院);Department of Computer Science and Engineering, Shanghai Jiao Tong University(上海交通大学计算机科学与工程学院)
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
University of Waterloo(滑铁卢大学);Sea AI Lab(Sea AI 实验室);University of Toronto(多伦多大学);Shanghai University(上海大学);HKUST(香港科技大学);M-A-P;National University of Singapore(新加坡国立大学)
Agentic AI for Scaling Diagnosis and Care in Neurodegenerative Disease
Goizueta Brain Health Institute, Emory University(埃默里大学戈伊苏埃塔大脑健康研究所);University of California, San Francisco(加州大学旧金山分校);Georgia Institute of Technology(佐治亚理工学院);University of California, Berkeley(加州大学伯克利分校)