AI Agent

Inferring land use from mobile phone activity

Jameson L. Toole, Michael Ulm, Dietmar Bauer, Marta C. Gonzalez

专题命中 GUI与网页智能体 ：planning(abstract)；分类 cs.LG

Comments To be presented at ACM UrbComp2012

Grey-box GUI Testing: Efficient Generation of Event Sequences

Stephan Arlt, Ishan Banerjee, Cristiano Bertolini, Atif M. Memon, Martin Schäf

专题命中 GUI与网页智能体 ：workflow(abstract)；分类 cs.SE

Comments 11 pages

A multiagent urban traffic simulation

Pierrick Tranouez, Eric Daudé, Patrice Langlois

专题命中 GUI与网页智能体 ：agent(abstract)；分类 cs.AI

Comments arXiv admin note: significant text overlap with arXiv:0909.1021 and arXiv:0910.1026

Journal ref Journal of Nonlinear Systems and Applications 1, 3 (2010) 9 pp (in print)

Integrated information increases with fitness in the evolution of animats

Jeffrey Edlund, Nicolas Chaumont, Arend Hintze, Christof Koch, Giulio Tononi, Christoph Adami

专题命中 GUI与网页智能体 ：agent(abstract)；分类 cs.AI

Comments 27 pages, 8 figures, one supplementary figure. Three supplementary video files available on request. Version commensurate with published text in PLoS Comput. Biol

Journal ref PLoS Computational Biology 7 (2001) e1002236

Learning Geometrically-Constrained Hidden Markov Models for Robot Navigation: Bridging the Topological-Geometrical Gap

L. P. Kaelbling, H. Shatkay

专题命中 GUI与网页智能体 ：planning(abstract)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 16, pages 167-207, 2002

Introduction to the iDian

Xin Rong

专题命中 GUI与网页智能体 ：agent(abstract)；分类 cs.AI

Comments 4 pages

Neural Networks in Mobile Robot Motion

Danica Janglova

专题命中 GUI与网页智能体 ：planning(abstract)；分类 cs.AI

Comments 9 Pages

Journal ref International Journal of Advanced Robotic Systems, Volume 1, Number 1, March 2004, pp.15-22

Verbal Interactions in Virtual Worlds

Pierre Nugues

专题命中 GUI与网页智能体 ：agent(abstract)；分类 cs.CL

Comments Position paper for CHI 2000 Workshop on Natural-Language Interaction, The Hague, 22 figures

Interactive Medical-SAM2 GUI: A Napari-based semi-automatic annotation tool for medical images

交互式医学-SAM2 GUI：基于Napari的半自动标注工具用于医学图像

Woojae Hong, Jong Ha Hwang, Jiyong Chung, Joongyeon Choi, Hyunggun Kim, Yong Hwy Kim

机构 * Department of Biomechatronic Engineering, Sungkyunkwan University（生物机电工程系，全州大学） ； Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine（神经外科，首尔国立大学医院，首尔国立大学医学院） 纠错

专题命中 GUI与网页智能体 ：workflow(abstract)；planning(comments)

AI总结 交互式医学-SAM2 GUI 提供基于Napari的本地工作流，实现高效的3D医学图像半自动标注与导出功能。

Comments Planning to submit JOSS (Journal of Open Source Software)

SwordRiding: A Unified Navigation Framework for Quadrotors in Unknown Complex Environments via Online Guiding Vector Fields

SwordRiding：一种基于在线引导矢量场的四旋翼无人机在未知复杂环境中的统一导航框架

Xuchen Liu, Ruocheng Li, Bin Xin, Weijia Yao, Qigeng Duan, Jinqiang Cui, Ben M. Chen, Jie Chen

机构 * Pengcheng Laboratory, Shenzhen, Guangdong, China（鹏城实验室，深圳，广东，中国） ； School of Automation, Beijing Institute of Technology, Beijing, China（自动化学院，北京理工大学，北京，中国） ； School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学） ； Department of Control Science and Engineering, Harbin Institute of Technology（控制科学与工程学院，哈尔滨工业大学） ； National Key Laboratory of Autonomous Intelligent Unmanned Systems（自主智能无人系统国家重点实验室） ； Department of Mechanical and Automation Engineering, the Chinese University of Hong Kong, Hong Kong, China（机械与自动化工程系，香港中文大学，香港，中国） 纠错

专题命中 GUI与网页智能体 ：planning(abstract,comments)

AI总结 SwordRiding提出了一种基于在线引导矢量场的四旋翼无人机统一导航框架，通过闭环导航提升在未知复杂环境中的实时适应性和鲁棒性。

Comments For an experimental demo, see https://www.youtube.com/watch?v=tKYCg266c4o. For the lemma proof, see https://github.com/SmartGroupSystems/GVF_close_loop_planning/blob/main/proofs.md

Embodied Vision-and-Language Navigation with Dynamic Convolutional Filters

Federico Landi, Lorenzo Baraldi, Massimiliano Corsini, Rita Cucchiara

专题命中 GUI与网页智能体 ：agent(abstract,comments)

Comments BMVC 2019 (Oral). Code is available at https://github.com/aimagelab/DynamicConv-agent

Collective fast delivery by energy-efficient agents

Andreas Bärtschi, Daniel Graf, Matus Mihalak

专题命中 GUI与网页智能体 ：agent(abstract,comments)

Comments In an extended abstract of this paper [MFCS 2018], we erroneously claimed the single agent approach for variant (iii) to have approximation ratio 2

Journal ref In 43rd International Symposium on Mathematical Foundations of Computer Science, MFCS'18, pages 56:1-56:16, 2018

Geo-Conquesting Based on Graph Analysis for Crowdsourced Metatrails from Mobile Sensing

Bo-Wei Chen, Wen Ji

专题命中 GUI与网页智能体 ：planning(abstract,comments)

Comments Mobile sensing, crowdsensing, crowdsourcing, graph analysis, graph mining, hotspot network, affinity network, transition network, geo-conquesting, intelligent marketing, smart footprint, smart city, urban planning, urban monitoring

VeCAS: Vessel-Focused Contrast-Free Angiogram Synthesis for Vascular Interventions

VeCAS：面向血管介入的聚焦血管的无造影剂血管造影合成

De-Xing Huang, Chen-Yu Wang, Hao Liang, Xiao-Hu Zhou, Mei-Jiang Gui, Tian-Yu Xiang, Qin-Yi Zhang, Chen Wang, Xiao-Liang Xie, Shi-Qi Liu, Ming-Yuan Liu, Zhen-Chang Wang, Zeng-Guang Hou

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 本文提出VeCAS框架，通过两阶段合成实现无造影剂血管造影，在下肢数据集实验中优于对比方法，还可缩短机器人导丝导航的时间与步骤，具临床应用潜力。

Comments 10 pages, 8 figures, 5 tabels, supplementary material: https://dxhuang-casia.github.io/data/vecas_supplementary_material.pdf

Multimodal-Language-Model-Driven Interaction and Companionship for Service Robots in Elderly-Care Facilities

面向养老机构服务机器人的多模态语言模型驱动的交互与陪伴

Ching-Chieh Liu, Cong-Thanh Vu, Yen-Chen Liu

机构 * National Cheng Kung University (NCKU)（成功大学） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 该研究针对养老机构服务机器人缺乏综合陪伴与安全能力的问题，提出整合主动视觉跟人、LLM语音交互及VLM安全监测的智能陪伴机器人系统，实验验证其跟随交互与跌倒检测的有效性。

Comments Accepted to the 2026 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

The Fallback as Signal: Preserved Human Skill, Liability, and Competence Signaling in Credence-Good Markets under Improving AI

作为信号的弃权：AI不断改进下的信任品市场中保留的人类技能、责任与能力信号

Andreas Bauer

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 该研究针对AI改进但仍不完善时企业的人类员工参与决策问题，构建基于主体的市场模型再现相关分析阈值，揭示信任品市场中人类技能等信号的保留机制。

Comments 51 pages, 7 figures. v3: corrections to the proofs in Appendices A and B (no reported number changes); Proposition 8 strengthened to an unconditional result with a closed-form threshold; declarations block added. Replication package: https://doi.org/10.6084/m9.figshare.33317559

Nori A3: A Bimanual Mobile Manipulator at the Appliance Price Point

Nori Bot：一款不到1000美元的 floor-to-counter 移动机械臂

Antonio Li

机构 * LeRobot 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 Nori Bot 通过600mm Z轴提升、Raspberry Pi 4与OpenClaw协同控制以及软件安全栈解决移动机械臂的三大限制，成本仅为同类商业平台的3%。

Comments 5 pages, 4 figures, 2 tables. Supersedes arXiv:2605.16537, which described an earlier prototype on a different mechanical base

PageGuide: Browser extension to assist users in navigating a webpage and locating information

PageGuide: 一款辅助用户在网页上导航和查找信息的浏览器扩展

Tin Nguyen, Thang T. Truong, Runtao Zhou, Trung Bui, Chirag Agarwal, Anh Totti Nguyen

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 PageGuide通过视觉叠加将LLM回答与HTML DOM结合，帮助用户快速定位信息、逐步指导操作并隐藏干扰内容，提升浏览效率和准确性。

Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments

针对现实动态环境中的GUI代理的环境注入攻击

Yitong Zhang, Ximo Li, Liyi Cai, Jia Li

机构 * College of AI, Tsinghua University（清华大学人工智能学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； School of Computer Science, Peking University（北京大学计算机学院） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 本文提出Chameleon框架，通过LLM驱动的环境模拟和注意力黑洞机制，有效暴露GUI代理在动态环境中的隐藏漏洞。

SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis

SwipeGen: 通过类人滑动合成弥合GUI代理的执行差距

Xuan Wang, Siyuan Su, Quantong Fu, Yongxiang Hu, Yangfan Zhou

机构 * College of Computer Science and Artificial Intelligence, Fudan University（计算机科学与人工智能学院，复旦大学） ； Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理重点实验室） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 SwipeGen通过合成类人滑动交互提升GUI代理的执行能力，实验显示其滑动执行准确率较基线提升214%。

Comments Accepted to ACM MM 2026. 10 pages

If, Then, Otherwise: Diagnosing Conditional Branching in Vision-Language Navigation

如果、那么、否则：诊断视觉-语言导航中的条件分支

Seoyoung Lee, Neel P. Bhatt, Pranay Samineni, Cong Liu, S P Sharan, Timothy Barclay, Gregory M. Wagner, Daniel Milan, Sandeep Chinchali, Ufuk Topcu, Atlas Wang

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Collins Aerospace（柯林斯航空航天公司） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 针对视觉-语言导航智能体的条件分支诊断需求，提出基于场景图的基准CondVLN及轻量级神经符号分支选择模型，可暴露智能体的逻辑决策失败并提升性能2倍。

Comments 11 pages, 1 figure, 3 tables. Project page: https://condvln.github.io/

Evaluating Beyond the Screen: Collective Assessment of AI-Generated Business Plans with Resource-Constrained Entrepreneurs

屏幕之外的评估：与资源受限创业者共同评估AI生成的商业计划书

Qi Zhao, Marjory Pineda, Ketul Chhaya, Aakash Gautam, Yasmine Kotturi

专题命中 GUI与网页智能体 ：planning(abstract)

AI总结 该研究针对资源受限创业者，将BizChat工具扩展出评估模块，通过小组讨论让14名参与者集体评估AI生成的商业计划，发现该方式能提升评估效果。

Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos

通过从野外视频进行可扩展学习揭示具身城市导航中的长尾分布

Bingyi Xia, Han Bao, Zhewei Chen, Hanjing Ye, Jingwen Yu, Yuhan Pang, Wenjun Xu, Jiankun Wang

专题命中 GUI与网页智能体 ：planning(abstract)

AI总结 该研究提出可扩展框架，从网络规模野外 egocentric 视频学习点目标城市导航策略，自动注释视频并训练视觉-语言-动作策略，表征并诊断导航长尾分布与失败模式，验证了知识迁移效果并揭示长尾结构。

VLM-Empowered Multi-Mode System for Efficient and Safe Planetary Navigation

Sinuo Cheng, Ruyi Zhou, Wenhao Feng, Huaiguang Yang, Haibo Gao, Zongquan Deng, Liang Ding

机构 * State Key Laboratory of Robotics and System, Harbin Institute of Technology（机器人系统国家重点实验室，哈尔滨工业大学） 纠错

专题命中 GUI与网页智能体 ：planning(abstract)

Comments accepted by IROS 2025

Spatiotemporal Tube-Based Safety-Certificate for Autonomous Navigation of Articulated Vehicles

铰接式车辆自主导航的基于时空管的安全证书

Mohd. Faizuddin Faruqui, Ratnangshu Das, Ravi Kumar L, Pushpak Jagtap

专题命中 GUI与网页智能体 ：planning(abstract)

AI总结 针对铰接式车辆自主导航的狭窄路线机动挑战，提出基于时空管的规划方法，确保挂车处于道路走廊内，经仿真验证可提供路线安全证书。

Comments Accepted for presentation at the 2026 IEEE International Conference on Intelligent Transportation Systems (ITSC 2026)

Designing Mobile and Wearable Sensor-Fused Conversational Agents for Health and Wellbeing

面向健康与福祉的移动及可穿戴传感器融合对话智能体设计

Hansoo Lee, Pablo Fonseca, Md Haseen Akhtar

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 本教程面向健康领域，旨在教授参与者使用WSDWAS工具，将可穿戴传感器数据与LLM驱动的对话智能体结合，实现从被动监测到可操作福祉对话的转变。

Comments 6 pages, 3 figures. Accepted as a Tutorial at the 28th International Conference on Mobile Human-Computer Interaction (MobileHCI '26)

Journal ref In 28th International Conference on Mobile Human-Computer Interaction (MobileHCI '26), August 31-September 03, 2026, Swansea, United Kingdom

Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigation

Graph-MambaNav：利用对象关系知识的时空图Mamba用于目标对象导航

Leyuan Sun, Genxin Chen, Linwei Ye, Yan Zhang, Xi Kan, Yanfei Sun

机构 * School of Internet of Things Engineering, Wuxi University（无锡大学物联网工程学院） ； School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications（南京邮电大学通信与信息工程学院） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 本研究提出Graph-MambaNav，一种结合LLM常识对象关系的目标感知时空图编码框架，通过节点排序与Mamba建模实现高效导航，在仿真环境表现优异且泛化性好，经真实机器人部署验证有效。

Comments Accepted by IEEE Robotics and Automation Letters (IEEE RA-L), will transfer to 2027 IEEE International Conference on Robotics & Automation (ICRA)

Koopman-Based Dynamic Environment Prediction for Safe UAV Navigation

Vitor Bueno, Ali Azarbahram, Marcello Farina, Lorenzo Fagiano

专题命中 GUI与网页智能体 ：planning(abstract)

Journal ref 2026 European Control Conference (ECC), IEEE

DaViNCi: A Dataset Towards Outdoor Vision-and-Language Navigation with Continuous Actions and Dynamic Elements

DaViNCi：面向包含连续动作与动态元素的户外视觉语言导航的数据集

Zihao Xie, Pingrui Lai, Yitong Wu, Hua Yang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 本文提出首个同时包含连续动作与动态元素的户外视觉语言导航数据集DaViNCi，通过实验验证其挑战性，为推动户外VLN向更真实环境发展提供实用支撑。

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

MemGUI-Bench: 动态环境中移动GUI代理内存能力的基准测试

Guangyi Liu, Pengxiang Zhao, Yaozhen Liang, Qinyi Luo, Shunye Tang, Yuxiang Chai, Weifeng Lin, Han Xiao, WenHao Wang, Siheng Chen, Zhengxi Lu, Gao Wu, Hao Wang, Liang Liu, Yong Liu

专题命中 GUI与网页智能体 ：agent(abstract)

AI总结 MemGUI-Bench提出一个综合的内存导向基准测试，通过128个任务评估移动GUI代理的内存能力，揭示了各系统中的显著内存缺陷并提出5种设计改进措施。

Comments Accepted to ACM MM 2026. Project page: https://memgui-bench.github.io/