AI Agent

Hybrid Motion Planning with Deep Reinforcement Learning for Mobile Robot Navigation

基于深度强化学习的混合运动规划用于移动机器人导航

Yury Kolomeytsev, Dmitry Golembiovsky

机构 * Department of Computational Mathematics and Cybernetics（计算数学与自动化系） ； Lomonosov Moscow State University（罗蒙诺夫莫斯科国立大学） 纠错

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

AI总结 本文提出HMP-DRL，结合基于图的全局规划与深度强化学习，提升移动机器人在复杂环境中的导航安全性和可靠性。

Comments 22 pages, 4 figures

From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents

从用户界面到代理界面：UI表示的效率优化以提升LLM代理性能

Dezhi Ran, Zhi Gong, Yuzhe Guo, Mengzhou Wu, Yuan Cao, Haochuan Lu, Hengyu Zhang, Xia Zeng, Gang Cao, Liangchao Yao, Yuetang Deng, Wei Yang, Tao Xie

机构 * Key Lab of HCST (PKU), MOE（HCST关键实验室（PKU），教育部） ； SCS, Peking University（SCS，北京大学） ； Tencent Inc.（腾讯公司） ； University of Texas at Dallas（德克萨斯大学达拉斯分校） 纠错

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

AI总结 UIFormer通过约束优化和结构分解，优化LLM代理的UI表示效率，实现令牌减少与性能提升的平衡。

Fara-7B: An Efficient Agentic Model for Computer Use

Fara-7B：一种高效的计算机使用代理模型

Ahmed Awadallah, Yash Lara, Raghav Magazine, Hussein Mozannar, Akshay Nambi, Yash Pandya, Aravind Rajeswaran, Corby Rosset, Alexey Taymanov, Vibhav Vineet, Spencer Whitehead, Andrew Zhao

专题命中 GUI与网页智能体 ：agentic(title,abstract)；分类 cs.AI、cs.CL

AI总结 Fara-7B通过合成数据生成系统训练出高效计算机使用代理模型，优于现有模型并在新基准测试中表现突出。

D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies

D-GARA：一种用于真实世界异常中GUI代理鲁棒性评估的动态基准框架

Sen Chen, Tong Zhao, Yi Bin, Fei Ma, Wenqi Shao, Zheng Wang

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

AI总结 D-GARA提出一种动态基准框架，用于评估Android GUI代理在真实世界异常中的鲁棒性，揭示了现有代理在异常环境下的性能下降问题。

Comments Accepted to AAAI 2026

ROSBag MCP Server: Analyzing Robot Data with LLMs for Agentic Embodied AI Applications

Lei Fu, Sahar Salimpour, Leonardo Militano, Harry Edelman, Jorge Peña Queralta, Giovanni Toffetti

专题命中 GUI与网页智能体 ：agentic(title,abstract)；分类 cs.AI、cs.SE

MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents

Yifan Xu, Xiao Liu, Xinghan Liu, Jiaqi Fu, Hanchen Zhang, Bohao Jing, Shudan Zhang, Yuting Wang, Wenyi Zhao, Yuxiao Dong

机构 * Tsinghua University（清华大学） 纠错

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

WAREX: Web Agent Reliability Evaluation on Existing Benchmarks

Su Kara, Fazle Faisal, Suman Nath

机构 * Stanford University（斯坦福大学） ； Microsoft Research（微软研究院） 纠错

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

VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verification

Jungjae Lee, Dongjae Lee, Chihun Choi, Youngmin Im, Jaeyoung Wi, Kihong Heo, Sangeun Oh, Sunjae Lee, Insik Shin

机构 * School of Computing, KAIST（计算机学院，韩国科学技术院） ； Korea University（韩国大学） ； Sungkyunkwan University（成均馆大学） 纠错

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

Visual Test-time Scaling for GUI Agent Grounding

Tiange Luo, Lajanugen Logeswaran, Justin Johnson, Honglak Lee

机构 * University of Michigan（密歇根大学） ； LG AI Research（LG人工智能研究） 纠错

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

Comments ICCV2025, https://github.com/tiangeluo/RegionFocus

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

Yucheng Shi, Wenhao Yu, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, Dong Yu

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

Comments 17 pages, 4 figures

Less is More: Empowering GUI Agent with Context-Aware Simplification

Gongwei Chen, Xurui Zhou, Rui Shao, Yibo Lyu, Kaiwen Zhou, Shuai Wang, Wentao Li, Yinchuan Li, Zhongang Qi, Liqiang Nie

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

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

Comments Accepted to ICCV 2025

BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism

Qinzhuo Wu, Pengzhi Gao, Wei Liu, Jian Luan

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

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Kevin Qinghong Lin, Linjie Li, Difei Gao, Zhengyuan Yang, Shiwei Wu, Zechen Bai, Weixian Lei, Lijuan Wang, Mike Zheng Shou

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

Comments Technical Report. Github: https://github.com/showlab/ShowUI

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu

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

Comments Accepted to ACL 2024 (main). Code and data is released at https://github.com/MinorJerry/WebVoyager

Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment

Chen Zhang, Qiang He, Zhou Yuan, Elvis S. Liu, Hong Wang, Jian Zhao, Yang Wang

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

Comments Accept at ICML 2024

UFO: A UI-Focused Agent for Windows OS Interaction

Chaoyun Zhang, Liqun Li, Shilin He, Xu Zhang, Bo Qiao, Si Qin, Minghua Ma, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

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

Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation

Vishnu Sashank Dorbala, James F. Mullen, Dinesh Manocha

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

Comments 10 pages

Journal ref IEEE Robotics and Automation Letters 9.5 (2024) 4083-4090

GPT-4V(ision) is a Generalist Web Agent, if Grounded

Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, Yu Su

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

Accessible Instruction-Following Agent

Kairui Zhou

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

On Jointly Optimizing Partial Offloading and SFC Mapping: A Cooperative Dual-agent Deep Reinforcement Learning Approach

Xinhan Wang, Huanlai Xing, Fuhong Song, Shouxi Luo, Penglin Dai, Bowen Zhao

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

Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

Weituo Hao, Chunyuan Li, Xiujun Li, Lawrence Carin, Jianfeng Gao

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

Comments To appear at CVPR 2020. The first two authors contributed equally to this manuscript. Code: https://github.com/weituo12321/PREVALENT

Agent Prioritization for Autonomous Navigation

Khaled S. Refaat, Kai Ding, Natalia Ponomareva, Stéphane Ross

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

Comments 8 pages, accepted to IEEE/RSJ International Conference on Robots and Systems (IROS) 2019

Cognitively-inspired Agent-based Service Composition for Mobile & Pervasive Computing

Oscar J. Romero

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

Comments This paper will appear on AIMS'19 (International Conference on Artificial Intelligence and Mobile Services) on June 25

Journal ref Artificial Intelligence and Mobile Services AIMS 2019

CoachAI: A Conversational Agent Assisted Health Coaching Platform

Ahmed Fadhil, Gianluca Schiavo, Yunlong Wang

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

Mobile Agent Based Solutions for Knowledge Assessment in elearning Environments

Mihaela Dinsoreanu, Cristian Godja, Claudiu Anghel, Ioan Salomie, Tom Coffey

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

A framework of reusable structures for mobile agent development

Tudor Marian, Bogdan Dumitriu, Mihaela Dinsoreanu, Ioan Salomie

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

The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation

Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira

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

Comments CVPR 2019 (Oral), our code is available at https://github.com/chihyaoma/regretful-agent

MAESTRO: Adapting GUIs and Guiding Navigation with User Preferences in Conversational Agents with GUIs

MAESTRO：在具有GUI的对话代理中通过用户偏好适应GUI并引导导航

Sangwook Lee, Adnan Abbas, Sang Won Lee, Young-Ho Kim, Yan Chen

专题命中 GUI与网页智能体 ：workflow(abstract,abstract_cn)；agent(abstract)；agentic(abstract)

AI总结 MAESTRO通过提取用户偏好并指导工作流导航，提升对话代理中GUI的适应性和导航效率，通过实验验证其有效性。

Comments 19 pages, 6 figures, 2 tables. Published at UIST '26. This is the camera-ready version, posted under CC BY 4.0

Journal ref Proceedings of the 39th Annual ACM Symposium on User Interface Software and Technology (UIST '26), November 2-5, 2026, Detroit, MI, USA

SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

SmartSnap: 为自主代理的主动证据寻求

Shaofei Cai, Yulei Qin, Haojia Lin, Zihan Xu, Gang Li, Yuchen Shi, Zongyi Li, Yong Mao, Siqi Cai, Xiaoyu Tan, Yitao Liang, Ke Li, Xing Sun

机构 * Tencent（腾讯） 纠错

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

AI总结 SmartSnap通过主动证据寻求机制，使自主代理在复杂任务中实现高效自我验证，提升性能并增强可靠性。

UISim: An Interactive Image-Based UI Simulator for Dynamic Mobile Environments

Jiannan Xiang, Yun Zhu, Lei Shu, Maria Wang, Lijun Yu, Gabriel Barcik, James Lyon, Srinivas Sunkara, Jindong Chen

机构 * University of California, San Diego (UCSD)（加州大学圣地亚哥分校） ； Google DeepMind（谷歌DeepMind） 纠错

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