多模态大模型

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

Guangyi Liu, Pengxiang Zhao, Yaozhen Liang, Liang Liu, Yaxuan Guo, Han Xiao, Weifeng Lin, Yuxiang Chai, Yue Han, Shuai Ren, Hao Wang, Xiaoyu Liang, WenHao Wang, Tianze Wu, Zhengxi Lu, Siheng Chen, LiLinghao, Hao Wang, Guanjing Xiong, Yong Liu, Hongsheng Li

专题命中 多模态Agent ：multimodal(abstract)

Comments Paper accepted to TMLR 2025, Project Homepage: https://github.com/PhoneLLM/Awesome-LLM-Powered-Phone-GUI-Agents

CFDagent: A Language-Guided, Zero-Shot Multi-Agent System for Complex Flow Simulation

Zhaoyue Xu, Long Wang, Chunyu Wang, Yixin Chen, Qingyong Luo, Hua-Dong Yao, Shizhao Wang, Guowei He

专题命中 多模态Agent ：multimodal(abstract)

Machine-Readable Ads: Accessibility and Trust Patterns for AI Web Agents interacting with Online Advertisements

Joel Nitu, Heidrun Mühle, Andreas Stöckl

专题命中 多模态Agent ：multimodal(abstract)

SafeFlow: Safe Robot Motion Planning with Flow Matching via Control Barrier Functions

Xiaobing Dai, Zewen Yang, Dian Yu, Fangzhou Liu, Hamid Sadeghian, Sami Haddadin, Sandra Hirche

机构 * Chair of Information-oriented Control (ITR), School of Computation, Information and Technology (CIT), Technical University of Munich (TUM)（信息导向控制教授职位、计算信息与技术学院（CIT）、慕尼黑技术大学（TUM）） ； Chair of Robotics and Systems Intelligence, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM)（机器人与系统智能教授职位、慕尼黑机器人与机器智能研究所（MIRMI）、慕尼黑技术大学（TUM）） ； Professorship of AI Planning in Dynamic Environments, School of Computation, Information and Technology (CIT), Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM)（动态环境中人工智能规划教授职位、计算信息与技术学院（CIT）、慕尼黑机器人与机器智能研究所（MIRMI）、慕尼黑技术大学（TUM）） ； National Key Laboratory of Modeling and Simulation for Complex Systems, Harbin Institute of Technology（复杂系统建模与仿真国家重点实验室、哈尔滨工业大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)

Human Machine Social Hybrid Intelligence:A Collaborative Decision Making Framework for Large Model Agent Groups and Human Experts

Ahmet Akkaya Melih, Yamuna Singh, Kunal L. Agarwal, Priya Mukherjee, Kiran Pattnaik, Hanuman Bhatia

专题命中 多模态Agent ：multi-modal(abstract)

Comments We have identified critical issues in the code implementation that severely deviate from Algorithm 1, invalidating all experimental results and conclusions. Despite exhaustive efforts to correct these issues, we find they fundamentally undermine the paper's core claims. To uphold academic integrity and prevent misinformation, we are withdrawing this manuscript

CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization

Irene Wang, Newsha Ardalani, Mostafa Elhoushi, Daniel Jiang, Samuel Hsia, Ekin Sumbul, Divya Mahajan, Carole-Jean Wu, Bilge Acun

机构 * Georgia Institute of Technology（佐治亚理工学院） ； FAIR at Meta（Meta的FAIR部门） ； Reality Labs at Meta（Meta的Reality Labs） ； Meta 纠错

专题命中 多模态Agent ：multi-modal(abstract)

Journal ref 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

RadioSim Agent: Combining Large Language Models and Deterministic EM Simulators for Interactive Radio Map Analysis

Sajjad Hussain, Conor Brennan

专题命中 多模态Agent ：multimodal(abstract)

Comments Submitted to EuCAP 2026

TumorMap: A Laser-based Surgical Platform for 3D Tumor Mapping and Fully-Automated Tumor Resection

Guangshen Ma, Ravi Prakash, Beatrice Schleupner, Jeffrey Everitt, Arpit Mishra, Junqin Chen, Brian Mann, Boyuan Chen, Leila Bridgeman, Pei Zhong, Mark Draelos, William C. Eward, Patrick J. Codd

机构 * Thomas Lord Department of Mechanical Engineering and Materials Science, Duke University（杜克大学机械工程与材料科学系） ； Department of Robotics, University of Michigan, Ann Arbor（密歇根大学机器人学系） ； Department of Orthopaedic Surgery, School of Medicine, Duke University（杜克大学骨科手术系） ； Department of Pathology, School of Medicine, Duke University（杜克大学病理学系） ； Department of Ophthalmology and Visual Sciences, University of Michigan Medical School, Ann Arbor（密歇根大学医学学院眼科与视觉科学系） ； Department of Neurosurgery, School of Medicine, Duke University（杜克大学神经外科系） 纠错

专题命中 多模态Agent ：multimodal(abstract)

Comments 41 pages, 25 figures

The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards

Sukai Huang, Shu-Wei Liu, Nir Lipovetzky, Trevor Cohn

机构 * Google DeepMind（谷歌DeepMind） 纠错

专题命中 多模态Agent ：multimodal(abstract)

Comments accepted by PRL Workshop Series @ ICAPS 2025. 11 main body pages, 21 appendix pages

Personalized Transcranial Electrical Stimulation: A Review of Computational Modeling and Optimization

Mo Wang, Kexin Zheng, Yingyue Xin, Xiang Chen, Yiling Liu, Huichun Luo, Jingsheng Tang, Tifei Yuan, Hongkai Wen, Pengfei Wei, Quanying Liu

专题命中 多模态Agent ：multimodal(abstract)

Individualizing Glioma Radiotherapy Planning by Optimization of Data and Physics-Informed Discrete Loss

Michal Balcerak, Jonas Weidner, Petr Karnakov, Ivan Ezhov, Sergey Litvinov, Petros Koumoutsakos, Tamaz Amiranashvili, Ray Zirui Zhang, John S. Lowengrub, Bene Wiestler, Bjoern Menze

专题命中 多模态Agent ：multi-modal(abstract)

Comments Accepted for publication in Nature Communications (DOI: 10.1038/s41467-025-60366-4)

Multiscale spatiotemporal heterogeneity analysis of bike-sharing system's self-loop phenomenon: Evidence from Shanghai

Yichen Wang, Qing Yu, Yancun Song

专题命中 多模态Agent ：multimodal(abstract)

Comments Critical OD data calibration errors in Sections 3.2/4.1 (invalidating indices, undermining conclusions), planning a revised validated version

Exploring Human-AI Interaction with Patient-Generated Health Data Sensemaking for Cardiac Risk Reduction

Pavithren V S Pakianathan, Rania Islambouli, Hannah McGowan, Diogo Branco, Tiago Guerreiro, Jan David Smeddinck

专题命中 多模态Agent ：multi-modal(abstract)

Comments Presented as demonstration at the workshop on visual analytics in healthcare (VAHC) (in conjunction with IEEE VIS 2025)

Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents

Geonsun Lee, Min Xia, Nels Numan, Xun Qian, David Li, Yanhe Chen, Achin Kulshrestha, Ishan Chatterjee, Yinda Zhang, Dinesh Manocha, David Kim, Ruofei Du

专题命中 多模态Agent ：multimodal(abstract)

A proof-theoretic approach to uniform interpolation property of multi-agent modal logic

Youan Su

专题命中 多模态Agent ：multi-modal(abstract)

Creating a customisable Socratic AI physics tutor

Eugenio Tufino, Bor Gregorcic

专题命中 多模态Agent ：multimodal(abstract)

Comments 7 pages, 3 figures

Journal ref Phys. Educ. 60 065037 (2025)

Designing Intent Communication for Agent-Human Collaboration

Yi Li, Francesco Chiossi, Helena Anna Frijns, Jan Leusmann, Julian Rasch, Robin Welsch, Philipp Wintersberger, Florian Michahelles, Albrecht Schmidt

专题命中 多模态Agent ：multi-modal(abstract)

Journal ref 24th International Conference on Mobile and Ubiquitous Multimedia - December 01--04, 2025

SafeDiver: Cooperative AUV-USV Assisted Diver Communication via Multi-agent Reinforcement Learning Approach

Tinglong Deng, Hang Tao, Xinxiang Wang, Yinyan Wang, Hanjiang Luo

专题命中 多模态Agent ：multimodal(abstract)

Comments Withdrawn to reorganize and extend the current findings in a future version

Review of Tools for Zero-Code LLM Based Application Development

Priyaranjan Pattnayak, Hussain Bohra

专题命中 多模态Agent ：multimodal(abstract)

Comments Accepted in 6th World Conference on Artificial Intelligence: Advances and Applications (WCAIAA 2025)

FlexBSS: A flexible multi-objective framework for bike-sharing station optimization

Jordi Grau-Escolano, David Duran-Rodas, Julian Vicens

专题命中 多模态Agent ：multimodal(abstract)

Comments 56 pages, 24 figures, 11 tables

Semi-Peaucellier Linkage and Differential Mechanism for Linear Pinching and Self-Adaptive Grasping

Haokai Ding, Zhaohan Chen, Tao Yang, Wenzeng Zhang

专题命中 多模态Agent ：multimodal(abstract)

Comments 6 pages, 9 figures, Accepted author manuscript for IEEE CASE 2025

Journal ref 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), Los Angeles, CA, USA, 2025, pp. 3441-3446

RunPacer: A Smartwatch-Based Vibrotactile Feedback System for Symmetric Co-Running by Visually Impaired Individuals and Guides

Yichen Yu, Huan-Song Xu, Ming-Yen Lin

专题命中 多模态Agent ：multimodal(abstract)

Comments 6 pages, 1 figure

Spatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planning

Aditya Chakravarty

专题命中 多模态Agent ：multimodal(abstract)

Journal ref NeurIPS 2025: Tackling Climate Change with Machine Learning Tackling Climate Change with Machine Learning: workshop at NeurIPS 2025

TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis

Haokun Zhao, Xiang Zhang, Jiaqi Wei, Yiwei Xu, Yuting He, Siqi Sun, Chenyu You

机构 * Stony Brook University（石溪大学） ； University of California, San Diego（加州大学圣地亚哥分校） ； University of British Columbia（不列颠哥伦比亚大学） ； Zhejiang University（浙江大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Case Western Reserve University（凯斯西储大学） ； Fudan University（复旦大学） 纠错

专题命中 多模态Agent ：multi-modal(abstract)

Unleashing Flow Policies with Distributional Critics

Deshu Chen, Yuchen Liu, Zhijian Zhou, Chao Qu, Yuan Qi

机构 * Fudan University（复旦大学） ； INFLY TECH (Shanghai) Co., Ltd（INFLY TECH（上海）有限公司） 纠错

专题命中 多模态Agent ：multimodal(abstract)

Towards Context-aware Mobile Privacy Notice: Implementation of A Deployable Contextual Privacy Policies Generator

Haochen Gong, Zhen Tao, Shidong Pan, Zhenchang Xing, Xiaoyu Sun

专题命中 多模态Agent ：multimodal(abstract)

Comments Accepted by ASE 2025, Tool Demonstration Track

PIE: Perception and Interaction Enhanced End-to-End Motion Planning for Autonomous Driving

Chengran Yuan, Zijian Lu, Zhanqi Zhang, Yimin Zhao, Zefan Huang, Shuo Sun, Jiawei Sun, Jiahui Li, Christina Dao Wen Lee, Dongen Li, Marcelo H. Ang

机构 * Department of Mechanical Engineering, National University of Singapore（机械工程系，国立新加坡大学） ； Department of Civil and Environmental Engineering, National University of Singapore（土木与环境工程系，国立新加坡大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)

Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning

Zengqi Peng, Yusen Xie, Yubin Wang, Rui Yang, Qifeng Chen, Jun Ma

机构 * Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)（机器人与自主系统方向，香港科学与技术大学（广州）） ； Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（计算机科学与工程系，香港科学与技术大学） ； Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology（陈家骏机器人研究所，香港科学与技术大学） 纠错

专题命中 多模态Agent ：multimodal(abstract)

Dynamic Objects Relocalization in Changing Environments with Flow Matching

Francesco Argenziano, Miguel Saavedra-Ruiz, Sacha Morin, Daniele Nardi, Liam Paull

机构 * Department of Computer, Automation and Management Engineering, Sapienza University of Rome（罗马大学计算机、自动化与管理工程系） ； Department of Computer Science and Operations Research, Université de Montréal（蒙特利尔大学计算机科学与运筹学系） ； Mila - Quebec AI Institute（魁北克人工智能研究所） 纠错

专题命中 多模态Agent ：multimodal(abstract)

CDFlow: Generative Gradient Flows for Configuration Space Distance Fields via Neural ODEs

Mengzhu Li, Yunyu Zhou, He Ying, F. Richard Yu

机构 * Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东人工智能与数字经济实验室） ； College of Design and Engineering（设计与工程学院） ； College of Computer Science and Software Engineering（计算机科学与软件工程学院） ； School of Information Technology（信息技术学院） 纠错

专题命中 多模态Agent ：multi-modal(abstract)