{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:27:47Z","timestamp":1787689667266,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","funder":[{"name":"Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study","award":["SN-ZJU-SIAS-001"],"award-info":[{"award-number":["SN-ZJU-SIAS-001"]}]},{"name":"National Natural Science Foundation of China","award":["62476244,62372399"],"award-info":[{"award-number":["62476244,62372399"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3785695","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2842-2853","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7514-3908","authenticated-orcid":false,"given":"Jingqi","family":"Yang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4100-5346","authenticated-orcid":false,"given":"Zhilong","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang Intelligence Indeed Technology Co., Ltd, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4752-2629","authenticated-orcid":false,"given":"Jiawei","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2621-6048","authenticated-orcid":false,"given":"Mingli","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-1041","authenticated-orcid":false,"given":"Sheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3665-1521","authenticated-orcid":false,"given":"Linjun","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang Intelligence Indeed Technology Co., Ltd, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3902-3101","authenticated-orcid":false,"given":"Xiaogang","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Zhejiang Intelligence Indeed Technology Co., Ltd, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6198-7481","authenticated-orcid":false,"given":"Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5890-4307","authenticated-orcid":false,"given":"Can","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_2_2_1","volume-title":"arXiv preprint arXiv:2502.13923","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_2_3_1","volume-title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale. (September","author":"Bonatti Rogerio","year":"2024","unstructured":"Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Jang, and Zack Hui. 2024. Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale. (September 2024)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27878"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"e_1_3_2_2_6_1","unstructured":"Daniel Chin Yuxuan Wang and Gus Xia. 2024. Human-Centered LLM-Agent User Interface: A Position Paper. arXiv:2405.13050 [cs.HC] https:\/\/arxiv.org\/abs\/2405.13050"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Xiang Deng Yu Gu Boyuan Zheng Shijie Chen Samuel Stevens Boshi Wang Huan Sun and Yu Su. 2023. Mind2Web: Towards a Generalist Agent for the Web. arXiv:2306.06070 [cs.CL]","DOI":"10.52202\/075280-1220"},{"key":"e_1_3_2_2_8_1","unstructured":"Team GLM Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Diego Rojas Guanyu Feng Hanlin Zhao Hanyu Lai Hao Yu Hongning Wang Jiadai Sun Jiajie Zhang Jiale Cheng Jiayi Gui Jie Tang Jing Zhang Juanzi Li Lei Zhao Lindong Wu Lucen Zhong Mingdao Liu Minlie Huang Peng Zhang Qinkai Zheng Rui Lu Shuaiqi Duan Shudan Zhang Shulin Cao Shuxun Yang Weng Lam Tam Wenyi Zhao Xiao Liu Xiao Xia Xiaohan Zhang Xiaotao Gu Xin Lv Xinghan Liu Xinyi Liu Xinyue Yang Xixuan Song Xunkai Zhang Yifan An Yifan Xu Yilin Niu Yuantao Yang Yueyan Li Yushi Bai Yuxiao Dong Zehan Qi Zhaoyu Wang Zhen Yang Zhengxiao Du Zhenyu Hou and Zihan Wang. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arXiv:2406.12793 [cs.CL]"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/AGILE.2011.23"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Wenyi Hong Weihan Wang Qingsong Lv Jiazheng Xu Wenmeng Yu Junhui Ji Yan Wang Zihan Wang Yuxiao Dong Ming Ding and Jie Tang. 2023. CogAgent: A Visual Language Model for GUI Agents. arXiv:2312.08914 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.729"},{"key":"e_1_3_2_2_12_1","unstructured":"Kevin Qinghong Lin Linjie Li Difei Gao Zhengyuan Yang Shiwei Wu Zechen Bai Weixian Lei Lijuan Wang and Mike Zheng Shou. 2024. ShowUI: One Vision-Language-Action Model for GUI Visual Agent. arXiv:2411.17465 [cs.CV] https:\/\/arxiv.org\/abs\/2411.17465"},{"key":"e_1_3_2_2_13_1","volume-title":"GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices. arXiv preprint arXiv:2406.08451","author":"Lu Quanfeng","year":"2024","unstructured":"Quanfeng Lu, Wenqi Shao, Zitao Liu, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, Yu Qiao, and Ping Luo. 2024. GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices. arXiv preprint arXiv:2406.08451 (2024)."},{"key":"e_1_3_2_2_14_1","unstructured":"Xing Han L\u00f9 Zden\u011bk Kasner and Siva Reddy. 2024. WebLINX: Real-World Website Navigation with Multi-Turn Dialogue. arXiv:2402.05930 [cs.CL]"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Dang Nguyen Jian Chen Yu Wang Gang Wu Namyong Park Zhengmian Hu Hanjia Lyu Junda Wu Ryan Aponte Yu Xia Xintong Li Jing Shi Hongjie Chen Viet Dac Lai Zhouhang Xie Sungchul Kim Ruiyi Zhang Tong Yu Mehrab Tanjim Nesreen K. Ahmed Puneet Mathur Seunghyun Yoon Lina Yao Branislav Kveton Thien Huu Nguyen Trung Bui Tianyi Zhou Ryan A. Rossi and Franck Dernoncourt. 2024. GUI Agents: A Survey. arXiv:2412.13501 [cs.AI] https:\/\/arxiv.org\/abs\/2412.13501","DOI":"10.18653\/v1\/2025.findings-acl.1158"},{"key":"e_1_3_2_2_16_1","unstructured":"OpenAI: Aaron Hurst Adam Lerer Adam P. Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford Aleksander M\u0105dry Alex Baker-Whitcomb Alex Beutel Alex Borzunov Alex Carney Alex Chow Alex Kirillov Alex Nichol Alex Paino Alex Renzin Alex Tachard Passos Alexander Kirillov Alexi Christakis Alexis Conneau Ali Kamali Allan Jabri Allison Moyer Allison Tam Amadou Crookes Amin Tootoochian Amin Tootoonchian Ananya Kumar Andrea Vallone Andrej Karpathy Andrew Braunstein Andrew Cann Andrew Codispoti Andrew Galu Andrew Kondrich Andrew Tulloch Andrey Mishchenko Angela Baek Angela Jiang Antoine Pelisse Antonia Woodford Anuj Gosalia Arka Dhar Ashley Pantuliano Avi Nayak Avital Oliver Barret Zoph Behrooz Ghorbani Ben Leimberger Ben Rossen Ben Sokolowsky Ben Wang Benjamin Zweig Beth Hoover Blake Samic Bob McGrew Bobby Spero Bogo Giertler Bowen Cheng Brad Lightcap Brandon Walkin Brendan Quinn Brian Guarraci Brian Hsu Bright Kellogg Brydon Eastman Camillo Lugaresi Carroll Wainwright Cary Bassin Cary Hudson Casey Chu Chad Nelson Chak Li Chan Jun Shern Channing Conger Charlotte Barette Chelsea Voss Chen Ding Cheng Lu Chong Zhang Chris Beaumont Chris Hallacy Chris Koch Christian Gibson Christina Kim Christine Choi Christine McLeavey Christopher Hesse Claudia Fischer Clemens Winter Coley Czarnecki Colin Jarvis Colin Wei Constantin Koumouzelis and Dane Sherburn et al. (318 additional authors not shown). 2024a. GPT-4o System Card. arXiv:2410.21276 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_2_2_17_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat Red Avila Igor Babuschkin Suchir Balaji Valerie Balcom Paul Baltescu Haiming Bao Mohammad Bavarian Jeff Belgum Irwan Bello Jake Berdine Gabriel Bernadett-Shapiro Christopher Berner Lenny Bogdonoff Oleg Boiko Madelaine Boyd Anna-Luisa Brakman Greg Brockman Tim Brooks Miles Brundage Kevin Button Trevor Cai Rosie Campbell Andrew Cann Brittany Carey Chelsea Carlson Rory Carmichael Brooke Chan Che Chang Fotis Chantzis Derek Chen Sully Chen Ruby Chen Jason Chen Mark Chen Ben Chess Chester Cho Casey Chu Hyung Won Chung Dave Cummings Jeremiah Currier Yunxing Dai Cory Decareaux Thomas Degry Noah Deutsch Damien Deville Arka Dhar David Dohan Steve Dowling Sheila Dunning Adrien Ecoffet Atty Eleti Tyna Eloundou David Farhi Liam Fedus Niko Felix Sim\u00f3n Posada Fishman Juston Forte Isabella Fulford Leo Gao Elie Georges Christian Gibson Vik Goel Tarun Gogineni Gabriel Goh Rapha Gontijo-Lopes Jonathan Gordon Morgan Grafstein Scott Gray Ryan Greene Joshua Gross Shixiang Shane Gu Yufei Guo Chris Hallacy Jesse Han Jeff Harris Yuchen He Mike Heaton Johannes Heidecke Chris Hesse Alan Hickey Wade Hickey Peter Hoeschele Brandon Houghton Kenny Hsu Shengli Hu Xin Hu Joost Huizinga Shantanu Jain and Shawn Jain et al. (181 additional authors not shown). 2024b. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_2_18_1","unstructured":"Yujia Qin Yining Ye Junjie Fang Haoming Wang Shihao Liang Shizuo Tian Junda Zhang Jiahao Li Yunxin Li Shijue Huang et al. 2025. UI-TARS: Pioneering Automated GUI Interaction with Native Agents. arXiv preprint arXiv:2501.12326 (2025)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Christopher Rawles Alice Li Daniel Rodriguez Oriana Riva and Timothy Lillicrap. 2023. Android in the Wild: A Large-Scale Dataset for Android Device Control. arXiv:2307.10088 [cs.LG] https:\/\/arxiv.org\/abs\/2307.10088","DOI":"10.52202\/075280-2609"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/347324.348993"},{"key":"e_1_3_2_2_21_1","volume-title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI. arXiv preprint arXiv:2205.11029","author":"Sun Liangtai","year":"2022","unstructured":"Liangtai Sun, Xingyu Chen, Lu Chen, Tianle Dai, Zichen Zhu, and Kai Yu. 2022. META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI. arXiv preprint arXiv:2205.11029 (2022)."},{"key":"e_1_3_2_2_22_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M. Dai Anja Hauth Katie Millican David Silver Melvin Johnson Ioannis Antonoglou Julian Schrittwieser Amelia Glaese Jilin Chen Emily Pitler Timothy Lillicrap Angeliki Lazaridou Orhan Firat James Molloy Michael Isard Paul R. Barham Tom Hennigan Benjamin Lee Fabio Viola Malcolm Reynolds Yuanzhong Xu Ryan Doherty Eli Collins Clemens Meyer Eliza Rutherford Erica Moreira Kareem Ayoub Megha Goel Jack Krawczyk Cosmo Du Ed Chi Heng-Tze Cheng Eric Ni Purvi Shah Patrick Kane Betty Chan Manaal Faruqui Aliaksei Severyn Hanzhao Lin YaGuang Li Yong Cheng Abe Ittycheriah Mahdis Mahdieh Mia Chen Pei Sun Dustin Tran Sumit Bagri Balaji Lakshminarayanan Jeremiah Liu Andras Orban Fabian G\u00fcra Hao Zhou Xinying Song Aurelien Boffy Harish Ganapathy Steven Zheng HyunJeong Choe \u00c1goston Weisz Tao Zhu Yifeng Lu Siddharth Gopal Jarrod Kahn Maciej Kula Jeff Pitman Rushin Shah Emanuel Taropa Majd Al Merey Martin Baeuml Zhifeng Chen Laurent El Shafey Yujing Zhang Olcan Sercinoglu George Tucker Enrique Piqueras Maxim Krikun Iain Barr Nikolay Savinov Ivo Danihelka Becca Roelofs Ana\u00efs White Anders Andreassen Tamara von Glehn Lakshman Yagati Mehran Kazemi Lucas Gonzalez Misha Khalman Jakub Sygnowski Alexandre Frechette Charlotte Smith Laura Culp Lev Proleev Yi Luan and Xi Chen et al. (1250 additional authors not shown). 2024. Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"e_1_3_2_2_23_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_2_24_1","unstructured":"Jialong Wu Wenbiao Yin Yong Jiang Zhenglin Wang Zekun Xi Runnan Fang Deyu Zhou Pengjun Xie and Fei Huang. 2025. WebWalker: Benchmarking LLMs in Web Traversal. arXiv:2501.07572 [cs.CL] https:\/\/arxiv.org\/abs\/2501.07572"},{"key":"e_1_3_2_2_25_1","volume-title":"Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu.","author":"Xie Tianbao","year":"2024","unstructured":"Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu. 2024. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. arXiv:2404.07972 [cs.AI]"},{"key":"e_1_3_2_2_26_1","unstructured":"Henry Hengyuan Zhao Difei Gao and Mike Zheng Shou. 2025. WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation. arXiv:2502.08047 [cs.AI] https:\/\/arxiv.org\/abs\/2502.08047"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3785695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:17:29Z","timestamp":1787689049000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3785695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":26,"alternative-id":["10.1145\/3770854.3785695","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3785695","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}