多模态大模型

GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices

Quanfeng Lu, Wenqi Shao, Zitao Liu, Lingxiao Du, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, Ping Luo

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； The University of Hong Kong（香港大学） ； Nanjing University（南京大学） ； Shanghai Jiao Tong University（上海交通大学） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CV

Comments 22 pages, 14 figures, ICCV 2025, a cross-app GUI navigation dataset

ADAgent: LLM Agent for Alzheimer's Disease Analysis with Collaborative Coordinator

Wenlong Hou, Guangqian Yang, Ye Du, Yeung Lau, Lihao Liu, Junjun He, Ling Long, Shujun Wang

机构 * 1 Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China 2 Amazon, USA 3 Shanghai Artificial Intelligence Laboratory, China 4 Department of Geriatrics, Third Affiliated Hospital of Sun Yat-sen University, China 5 Research Institute for Smart Ageing, The Hong Kong Polytechnic University, Hong Kong SAR, China 纠错

专题命中 多模态Agent ：multi-modal(abstract)；分类 cs.CV

DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery

Kun Li, Zhennan Wu, Shoupeng Wang, Jia Wu, Shirui Pan, Wenbin Hu

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments 29 pages, 8 figures, 2 tables

Efficient and Scalable Agentic AI with Heterogeneous Systems

Zain Asgar, Michelle Nguyen, Sachin Katti

机构 * Stanford University（斯坦福大学） ； Gimlet Labs Inc.（Gimlet实验室） ； Intel（英特尔） 纠错

专题命中 多模态Agent ：multi-modal(abstract)；分类 cs.AI

Comments Early access preprint

HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization

Benjamin Coriat, Eric Benhamou

机构 * CentraleSupelec（中央理工-巴黎高等电子学院） ； Ai for Alpha IJCAI 2025 - FinLLM Workshop（IJCAI 2025 年 FinLLM 工作坊） 纠错

专题命中 多模态Agent ：cross-modal(abstract)；分类 cs.AI

MMS Player: an open source software for parametric data-driven animation of Sign Language avatars

Fabrizio Nunnari, Shailesh Mishra, Patrick Gebhard

机构 * German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI）） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CL

Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction

Ce Zhang, Yale Song, Ruta Desai, Michael Louis Iuzzolino, Joseph Tighe, Gedas Bertasius, Satwik Kottur

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Meta 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CV

Towards Autonomous Riding: A Review of Perception, Planning, and Control in Intelligent Two-Wheelers

Mohammed Hassanin, Mohammad Abu Alsheikh, Carlos C. N. Kuhn, Damith Herath, Dinh Thai Hoang, Ibrahim Radwan

机构 * Faculty of Science & Technology, University of Canberra（科学与技术学院，堪培拉大学） ； OpenSI - Faculty of Science and Technology, University of Canberra（OpenSI - 科学与技术学院，堪培拉大学） ； School of Electrical and Data Engineering, University of Technology Sydney（电气与数据工程学院，悉尼技术大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CV

Comments 17 pages

MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications

Aleksandr Algazinov, Matt Laing, Paul Laban

机构 * Tsinghua University（清华大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers

Santhosh Kumar Ravindran

机构 * Microsoft Corporation（微软公司） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact

Rizwan Qureshi, Ranjan Sapkota, Abbas Shah, Amgad Muneer, Anas Zafar, Ashmal Vayani, Maged Shoman, Abdelrahman B. M. Eldaly, Kai Zhang, Ferhat Sadak, Shaina Raza, Xinqi Fan, Ravid Shwartz-Ziv, Hong Yan, Vinjia Jain, Aman Chadha, Manoj Karkee, Jia Wu, Seyedali Mirjalili

机构 * Center for research in Computer Vision, University of Central Florida（计算机视觉研究中心，中央佛罗里达大学） ； Cornell University（康奈尔大学） ； Department of Electronics Engineering, Mehran University of Engineering & Technology（电子工程系，工程与技术大学） ； Department of Imaging Physics, The University of Texas MD Anderson Cancer Center（成像物理系，德克萨斯大学MD安德森癌症中心） ； Intelligent Transportation Systems, University of Tennessee（智能交通运输系统，田纳西大学） ； Department of Electrical Engineering, City University of Hong Kong（电气工程系，香港城市大学） ； Department of Mechanical Engineering, Bartin University（机械工程系，巴廷大学） ； Vector Institute, Toronto Canada（多伦多加拿大向量研究所） ； Manchester Metropolitan University（曼彻斯特 Metropolitan 大学） ； Center for Data Science, New York University（数据科学中心，纽约大学） ； Meta Research（Meta 研究） ； Amazon Research（亚马逊研究） ； Centre for Artificial Intelligence Research and Optimization, Torrens University Australia（人工智能研究与优化中心，塔伦斯大学澳大利亚） ； University Research and Innovation Center, Obuda University（研究与创新中心，奥布达大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Introspection of Thought Helps AI Agents

Haoran Sun, Shaoning Zeng

机构 * Yangtze Delta Region Institute (Huzhou), University of Electronic and Science Technology of China（长江三角洲地区研究院（湖州），电子科技大学） ； School of Information and Software Engineering, University of Electronic and Science Technology of China（信息与软件工程学院，电子科技大学） ； Zhejiang Chuangjiekedong Ltd., Huzhou, Zhejiang, China（浙江创捷科技有限公司，湖州，浙江，中国） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning

Shibo Sun, Xue Li, Donglin Di, Mingjie Wei, Lanshun Nie, Wei-Nan Zhang, Dechen Zhan, Yang Song, Lei Fan

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； University of New South Wales（新南威尔士大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CL

SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments

Tianshun Li, Tianyi Huai, Zhen Li, Yichun Gao, Haoang Li, Xinhu Zheng

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments 8 pages, 9 figures, has been accepted by IROS 2025

AI-Driven Scholarly Peer Review via Persistent Workflow Prompting, Meta-Prompting, and Meta-Reasoning

Evgeny Markhasin

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments 23 pages, 37 pages (references and appendixes)

LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving

Yuhang Zhang, Jiaqi Liu, Chengkai Xu, Peng Hang, Jian Sun

机构 * College of Transportation, Tongji University（同济大学交通运输学院） 纠错

专题命中 多模态Agent ：multi-modal(abstract)；分类 cs.AI

Aria-UI: Visual Grounding for GUI Instructions

Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Chao Huang, Junnan Li

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments ACL 2025

Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving

Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon

机构 * Electrical and Computer Engineering（电气与计算机工程） ； University of Michigan–Dearborn（密歇根大学-迪尔伯恩分校） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Embodied AI Agents: Modeling the World

Pascale Fung, Yoram Bachrach, Asli Celikyilmaz, Kamalika Chaudhuri, Delong Chen, Willy Chung, Emmanuel Dupoux, Hongyu Gong, Hervé Jégou, Alessandro Lazaric, Arjun Majumdar, Andrea Madotto, Franziska Meier, Florian Metze, Louis-Philippe Morency, Théo Moutakanni, Juan Pino, Basile Terver, Joseph Tighe, Paden Tomasello, Jitendra Malik

机构 * Meta AI Research（Meta AI 研究） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

WebNav: An Intelligent Agent for Voice-Controlled Web Navigation

Trisanth Srinivasan, Santosh Patapati

机构 * Dept. of Applied AI（应用人工智能系） ； Cyrion Labs（Cyrian实验室） ； Dallas, USA（美国达拉斯） 纠错

专题命中 多模态Agent ：multi-modal(abstract)；分类 cs.AI

Intelligent Histology for Tumor Neurosurgery

Xinhai Hou, Akhil Kondepudi, Cheng Jiang, Yiwei Lyu, Samir Harake, Asadur Chowdury, Anna-Katharina Meißner, Volker Neuschmelting, David Reinecke, Gina Furtjes, Georg Widhalm, Lisa Irina Koerner, Jakob Straehle, Nicolas Neidert, Pierre Scheffler, Juergen Beck, Michael Ivan, Ashish Shah, Aditya Pandey, Sandra Camelo-Piragua, Dieter Henrik Heiland, Oliver Schnell, Chris Freudiger, Jacob Young, Melike Pekmezci, Katie Scotford, Shawn Hervey-Jumper, Daniel Orringer, Mitchel Berger, Todd Hollon

机构 * Department of Neurosurgery, University of Michigan, Ann Arbor, MI, USA（密歇根大学神经外科部） ； Department of Neurosurgery, University Hospital Cologne, Cologne, Germany（科隆大学医院神经外科部） ； Department of Neurosurgery, Medical University of Vienna, Vienna, Austria（维也纳医学大学神经外科部） ； Department of Neurosurgery, University Medical Center Freiburg, Freiburg, Germany（弗赖堡大学医学中心神经外科部） ； Department of Neurosurgery, University of Miami, Miami, FL, USA（迈阿密大学神经外科部） ； Department of Pathology, University of Michigan, Ann Arbor, MI, USA（密歇根大学病理学部） ； Department of Neurosurgery, University Hospital Erlangen, Erlangen, Germany（埃朗根大学医院神经外科部） ； Invenio Imaging Inc., Santa Clara, CA, USA（Invenio Imaging公司） ； Department of Neurosurgery, University of California, San Francisco, CA, USA（加州大学旧金山分校神经外科部） ； Department of Neurosurgery, NYU Langone Health, New York, NY, USA（纽约大学Langone健康中心神经外科部） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CV

BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments

Yibo Qiu, Zan Huang, Zhiyu Wang, Handi Liu, Yiling Qiao, Yifeng Hu, Shu'ang Sun, Hangke Peng, Ronald X Xu, Mingzhai Sun

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Embodied Instruction Following in Unknown Environments

Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Hang Yin, Yinan Liang, Angyuan Ma, Jiwen Lu, Haibin Yan

机构 * School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（北京邮电大学智能工程与自动化学院） ； School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院） ； Department of Automation, Tsinghua University（清华大学自动化学院） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments Project Page: https://gary3410.github.io/eif_unknown/

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Yupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang, Yuhang Zheng, Yinfeng Gao, Pengfei Li, Teng Zhang, Zhongpu Xia, Peng Jia, Dongbin Zhao

机构 * CASIA（中国科学院自动化研究所） ； Li Auto（力汽车） ； PCL（鹏城实验室） ； NUS（新加坡国立大学） ； Tsinghua（清华大学） 纠错

专题命中 多模态Agent ：multi-modal(abstract)；分类 cs.CV

Comments ICCV 2025, first version

A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning

Jiachen Zhong, Yiting Wang, Di Zhu, Ziwei Wang

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CV

Comments This request is based on the fact that one of the co-authors is a PhD student whose advisor has informed her that she was not authorized to publicly release this work without his prior approval. Unfortunately, this approval was not obtained, and as such, the submission was made without proper institutional and supervisory consent

BIMgent: Towards Autonomous Building Modeling via Computer-use Agents

Zihan Deng, Changyu Du, Stavros Nousias, André Borrmann

机构 * Chair of Computing in Civil and Building Engineering, Technical University of Munich, Germany（土木与建筑工程计算系，慕尼黑技术大学） ； TUM Georg Nemetschek Institute, Munich, Germany（慕尼黑技术大学Georg Nemetschek研究所） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments ICML 2025 Workshop on Computer Use Agents

ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining

Kexin Chen, Yuyang Du, Junyou Li, Hanqun Cao, Menghao Guo, Xilin Dang, Lanqing Li, Jiezhong Qiu, Pheng Ann Heng, Guangyong Chen

机构 * The Chinese University of Hong Kong, New Territories, Hong Kong SAR（香港中文大学） ； Zhejiang Lab, Zhejiang University, Hangzhou, China（浙江大学杭州实验室） ； Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, China（中国科学院杭州医学研究所） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

A Different Approach to AI Safety: Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety

Camille François, Ludovic Péran, Ayah Bdeir, Nouha Dziri, Will Hawkins, Yacine Jernite, Sayash Kapoor, Juliet Shen, Heidy Khlaaf, Kevin Klyman, Nik Marda, Marie Pellat, Deb Raji, Divya Siddarth, Aviya Skowron, Joseph Spisak, Madhulika Srikumar, Victor Storchan, Audrey Tang, Jen Weedon

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety

A Novel Framework for Integrating 3D Ultrasound into Percutaneous Liver Tumour Ablation

Shuwei Xing, Derek W. Cool, David Tessier, Elvis C. S. Chen, Terry M. Peters, Aaron Fenster

机构 * Robarts Research Institute, Western University, London, Canada（罗巴茨研究所在西蒙大学伦敦分校） ； School of Biomedical Engineering, Western University, London, Canada（生物医学工程学院，西蒙大学伦敦分校） ； Department of Medical Biophysics, Western University, London, Canada（医学生物物理学系，西蒙大学伦敦分校） ； Department of Electrical and Computer Engineering, Western University, London, Canada（电气与计算机工程系，西蒙大学伦敦分校） ； Department of Medical Imaging, Western University, London, Canada（医学影像系，西蒙大学伦敦分校） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI

Comments 11 pages, 5 figures

API Agents vs. GUI Agents: Divergence and Convergence

Chaoyun Zhang, Shilin He, Liqun Li, Si Qin, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

机构 * Microsoft（微软） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.AI