AI Agent

Learning to Navigate in Complex Environments

Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell

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

Comments 11 pages, 5 appendix pages, 11 figures, 3 tables, under review as a conference paper at ICLR 2017

Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment

推进移动GUI代理：一种以验证器驱动的方法用于实际部署

Gaole Dai, Shiqi Jiang, Ting Cao, Yuanchun Li, Yuqing Yang, Rui Tan, Mo Li, Lili Qiu

机构 * Nanyang Technological University（南洋理工大学） ； Microsoft Research（微软研究院） ； Tsinghua University（清华大学） 纠错

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

AI总结 V-Droid通过验证器驱动的方法提升移动GUI任务自动化代理的性能与效率

Comments "V-Droid: Advancing Mobile GUI Agent Through Generative Verifiers", got accepted to MobiCom 2026

EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI

EmbodiedGen V2：用于具身人工智能的具有智能体特性、可用于模拟的3D世界引擎

Xinjie Wang, Liu Liu, Taojun Ding, Andrew Choi, Chaodong Huang, Mengao Zhao, Ziang Li, Jackson Jiang, Chunlei Yu, Shengxiang Liu, Wei Xu, Zhizhong Su

机构 * Horizon Robotics（地平线机器人） ； WuwenAI（悟文智能） 纠错

专题命中 GUI与网页智能体 ：agentic(title)

AI总结 研究提出EmbodiedGen V2这个用于具身智能的3D世界引擎，通过统一表示解决资产组装问题。其生成环境支持多种任务，评估中资产管道表现良好，强化学习提升了模拟成功率，确立了它作为可扩展模拟基础设施的地位。

Comments Minor revisions to presentation; technical content and results remain unchanged. Project page: horizonrobotics.github.io/EmbodiedGen

Optimal strategies for driving a mobile agent in a guidance by repulsion model

在排斥引导模型中驱动移动代理的最优策略

Ramón Escobedo, Aitziber Ibañez, Enrique Zuazua

专题命中 GUI与网页智能体 ：agent(title)

AI总结 本文研究了在排斥引导模型中通过控制单一参数来驱动逃避者向目标移动的最优策略，提出反馈控制法以减少规避模式的使用并降低成本。

MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

MolmoWeb：开放视觉网络代理和开放数据用于开放网络

Tanmay Gupta, Piper Wolters, Zixian Ma, Peter Sushko, Rock Yuren Pang, Diego Llanes, Yue Yang, Taira Anderson, Boyuan Zheng, Zhongzheng Ren, Harsh Trivedi, Taylor Blanton, Caleb Ouellette, Winson Han, Ali Farhadi, Ranjay Krishna

机构 * Allen Institute for AI（艾伦人工智能研究所） ； University of Washington（华盛顿大学） 纠错

专题命中 GUI与网页智能体 ：agent(title)

AI总结 本文提出MolmoWeb，一个开放的多模态网络代理，通过公开的浏览器任务演示和网页GUI感知数据，实现状态-of-the-art的网络代理性能，促进开放研究。

Comments https://allenai.org/blog/molmoweb

SCRAMPPI: Efficient Contingency Planning for Mobile Robot Navigation via Hamilton-Jacobi Reachability

SCRAMPPI: 通过哈密顿-雅可比可达性实现移动机器人导航的高效应急规划

Raj Harshit Srirangam, Leonard Jung, Rohith Poola, Michael Everett

机构 * Northeastern University（东北大学） 纠错

专题命中 GUI与网页智能体 ：planning(title)

AI总结 本文提出SCRAMPPI算法，通过哈密顿-雅可比可达性分析实现移动机器人导航中的应急规划，结合采样基于规划器（MPPI）提升采样效率，实现实时生成主计划和应急计划。

Comments 8 pages, 5 figures

Wireless Context Engineering for Efficient Mobile Agentic AI and Edge General Intelligence

无线上下文工程用于高效的移动群体AI和边缘通用智能

Changyuan Zhao, Jiacheng Wang, Yunting Xu, Geng Sun, Dusit Niyato, Zan Li, Abbas Jamalipour, Dong In Kim

专题命中 GUI与网页智能体 ：agentic(title)

AI总结 本文提出无线上下文工程，通过优化无线边缘智能的上下文管理，提升移动群体AI和边缘通用智能的效率。

Comments 7 pages, 4 figures

Agile and Safe Trajectory Planning for Quadruped Navigation with Motion Anisotropy Awareness

具备运动各向异性意识的四足机器人导航轨迹规划

Wentao Zhang, Shaohang Xu, Peiyuan Cai, Lijun Zhu

机构 * School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China（华中科技大学人工智能与自动化学院） 纠错

专题命中 GUI与网页智能体 ：planning(title)

AI总结 本文提出了一种考虑四足机器人运动各向异性的导航框架，通过轨迹生成与优化提升导航效率和安全性。

Comments 8 pages, 6 figures, submitted to 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent

AFRAgent：一种基于自适应特征归一化的高分辨率感知GUI代理

Neeraj Anand, Rishabh Jain, Sohan Patnaik, Balaji Krishnamurthy, Mausoom Sarkar

机构 * Media and Data Science Research, Adobe（Adobe媒体与数据科学研究所） 纠错

专题命中 GUI与网页智能体 ：agent(title)

AI总结 AFRAgent通过自适应特征归一化技术，在保持高分辨率细节的同时，实现了更高效的GUI自动化性能，比现有模型小四分之一。

Comments Accepted at WACV 2026 Conference

Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation

Badi Li, Ren-jie Lu, Yu Zhou, Jingke Meng, Wei-shi Zheng

机构 * Sun Yat-sen University（中山大学） ； The University of Hong Kong（香港大学） ； Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与高级计算重点实验室） 纠错

专题命中 GUI与网页智能体 ：agent(title)

Next-Gen Museum Guides: Autonomous Navigation and Visitor Interaction with an Agentic Robot

Luca Garello, Francesca Cocchella, Alessandra Sciutti, Manuel Catalano, Francesco Rea

专题命中 GUI与网页智能体 ：agentic(title)

LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs

Xinyuan Zhang, Yonglin Tian, Fei Lin, Yue Liu, Jing Ma, Kornélia Sára Szatmáry, Fei-Yue Wang

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室） ； Department of Engineering Science, Faculty of Innovation Engineering, Macau University of Science and Technology（澳门科技大学创新工程学院工程科学系） ； China Ship Research and Development Academy（中国船舶科研 Academy） ； Obuda University（奥布达大学） ； State Key Laboratory for Management and Control of Complex Systems, Chinese Academy of Sciences（中国科学院复杂系统管理与控制国家重点实验室） 纠错

专题命中 GUI与网页智能体 ：agentic(title)

BaSeNet: A Learning-based Mobile Manipulator Base Pose Sequence Planning for Pickup Tasks

Lakshadeep Naik, Sinan Kalkan, Sune L. Sørensen, Mikkel B. Kjærgaard, Norbert Krüger

专题命中 GUI与网页智能体 ：planning(title)

Comments Submitted to IROS 2024

Journal ref 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

MobileFlow: A Multimodal LLM For Mobile GUI Agent

Songqin Nong, Jiali Zhu, Rui Wu, Jiongchao Jin, Shuo Shan, Xiutian Huang, Wenhao Xu

专题命中 GUI与网页智能体 ：agent(title)

Route planning of mobile sensing fleets for repeatable visits

Wen Ji, Ke Han, Qian Ge

专题命中 GUI与网页智能体 ：planning(title)

Comments 24 pages, 5 figures, 4 tables

Collision-free Motion Planning for Mobile Robots by Zero-order Robust Optimization-based MPC

Yunfan Gao, Florian Messerer, Jonathan Frey, Niels van Duijkeren, Moritz Diehl

专题命中 GUI与网页智能体 ：planning(title)

Towards social embodied cobots: The integration of an industrial cobot with a social virtual agent

Matteo Lavit Nicora, Sebastian Beyrodt, Dimitra Tsovaltzi, Fabrizio Nunnari, Patrick Gebhard, Matteo Malosio

专题命中 GUI与网页智能体 ：agent(title)

LOKO: Localization-aware Roll-out Planning for Future Mobile Networks

Antonio Albanese, Vincenzo Sciancalepore, Albert Banchs, Xavier Costa-Pérez

专题命中 GUI与网页智能体 ：planning(title)

Journal ref IEEE Transactions on Mobile Computing (Early Access), 2021

Sharing Cognition: Human Gesture and Natural Language Grounding Based Planning and Navigation for Indoor Robots

Gourav Kumar, Soumyadip Maity, Ruddra dev Roychoudhury, Brojeshwar Bhowmick

专题命中 GUI与网页智能体 ：planning(title)

Mobile Recharger Path Planning and Recharge Scheduling in a Multi-Robot Environment

Tanmoy Kundu, Indranil Saha

专题命中 GUI与网页智能体 ：planning(title)

Belief Space Planning for Mobile Robots with Range Sensors using iLQG

Ke Sun, Vijay Kumar

专题命中 GUI与网页智能体 ：planning(title)

Comments Accepted by Robotics and Automation Letters

A realistic agent-based simulation model for COVID-19 based on a traffic simulation and mobile phone data

Sebastian A. Müller, Michael Balmer, William Charlton, Ricardo Ewert, Andreas Neumann, Christian Rakow, Tilmann Schlenther, Kai Nagel

专题命中 GUI与网页智能体 ：agent(title)

Fair navigation planning: a humanitarian robot use case

Martim Brandao

专题命中 GUI与网页智能体 ：planning(title)

Comments Appeared at the KDD 2020 Workshop on Humanitarian Mapping

Planning an Efficient and Robust Base Sequence for a Mobile Manipulator Performing Multiple Pick-and-place Tasks

Jingren Xu, Kensuke Harada, Weiwei Wan, Toshio Ueshiba, Yukiyasu Domae

专题命中 GUI与网页智能体 ：planning(title)

Comments To appear in ICRA 2020, check out https://www.youtube.com/watch?v=rEgFJe4m0q4&t=15s for the video demonstration

User Association and Path Planning for UAV-Aided Mobile Edge Computing with Energy Restriction

Yuwen Qian, Feifei Wang, Jun Li, Long Shi, Kui Cai, Feng Shu

专题命中 GUI与网页智能体 ：planning(title)

Comments Accepted by IEEE WCL

Mapping, Localization and Path Planning for Image-based Navigation using Visual Features and Map

Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Thomas Probst, Luc Van Gool

专题命中 GUI与网页智能体 ：planning(title)

Comments CVPR 2019, for implementation see https://github.com/janinethoma

Combination interventions for Hepatitis C and Cirrhosis reduction among people who inject drugs: An agent-based, networked population simulation experiment

Bilal Khan, Ian Duncan, Mohamad Saad, Daniel Schaefer, Ashly Jordan, Daniel Smith, Alan Neaigus, Don Des Jarlais, Holly Hagan, Kirk Dombrowski

专题命中 GUI与网页智能体 ：agent(title)

Learning to Navigate: Exploiting Deep Networks to Inform Sample-Based Planning During Vision-Based Navigation

Justin S. Smith, Jin-Ha Hwang, Fu-Jen Chu, Patricio A. Vela

专题命中 GUI与网页智能体 ：planning(title)

Comments 7 pages, 6 figures

Mobile Edge Computing via a UAV-Mounted Cloudlet: Optimization of Bit Allocation and Path Planning

Seongah Jeong, Osvaldo Simeone, Joonhyuk Kang

专题命中 GUI与网页智能体 ：planning(title)

Comments 14 pages, 5 figures, 2 tables, IEEE Transactions on Vehicular Technology

Dynamic Path Planning and Replanning for Mobile Robots using RRT*

Devin Connell, Hung Manh La

专题命中 GUI与网页智能体 ：planning(title)