{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:40:11Z","timestamp":1759012811572,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747780","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:44:49Z","timestamp":1758959089000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Click: Cross-Tab Web Automation via Action Generalization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0513-7403","authenticated-orcid":false,"given":"Jiacheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information, University of Michigan, Ann Arbor, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6906-225X","authenticated-orcid":false,"given":"Jiawen","family":"Li","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9040-4313","authenticated-orcid":false,"given":"Maryam","family":"Arab","sequence":"additional","affiliation":[{"name":"School of Information, University Of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5823-1499","authenticated-orcid":false,"given":"Steve","family":"Oney","sequence":"additional","affiliation":[{"name":"School of Information, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. Basic editing \u2014 code.visualstudio.com. https:\/\/code.visualstudio.com\/docs\/editing\/codebasics##_multiple-selections-multicursor. [Accessed 25-03-2025]."},{"key":"e_1_3_3_2_3_2","unstructured":"[n. d.]. Beautiful soup. https:\/\/www.crummy.com\/software\/BeautifulSoup\/. [Accessed 29-03-2025]."},{"key":"e_1_3_3_2_4_2","unstructured":"[n. d.]. Cypress. https:\/\/www.cypress.io\/ . [Accessed 30-03-2025]."},{"key":"e_1_3_3_2_5_2","unstructured":"[n. d.]. Multiple selection with the keyboard \u2014 www.sublimetext.com. https:\/\/www.sublimetext.com\/docs\/multiple_selection_with_the_keyboard.html. [Accessed 01-04-2025]."},{"key":"e_1_3_3_2_6_2","unstructured":"[n. d.]. Operator \u2014 operator.chatgpt.com. https:\/\/operator.chatgpt.com\/. [Accessed 05-04-2025]."},{"key":"e_1_3_3_2_7_2","unstructured":"[n. d.]. Puppeteer. https:\/\/pptr.dev. [Accessed 29-03-2025]."},{"key":"e_1_3_3_2_8_2","unstructured":"[n. d.]. Selenium. https:\/\/www.selenium.dev. [Accessed 01-03-2025]."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"I\u00f1igo Aldalur Alain Perez and Felix Larrinaga. 2021. Web augmentation as a technique to diminish user interactions in repetitive tasks. IEEE Access 9 (2021) 112686\u2013112704.","DOI":"10.1109\/ACCESS.2021.3104187"},{"key":"e_1_3_3_2_10_2","unstructured":"Axiom.ai. 2024. No-Code Browser Automation. https:\/\/axiom.ai\/. Accessed: September 2024."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Shaon Barman Sarah\u00a0E. Chasins Rastislav Bod\u00edk and Sumit Gulwani. 2016. Ringer: web automation by demonstration. Proceedings of the 2016 ACM SIGPLAN International Conference on Object-Oriented Programming Systems Languages and Applications (2016). 10.1145\/2983990.2984020","DOI":"10.1145\/2983990.2984020"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/1125451.1125570"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/1095034.1095062"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242661"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606720"},{"key":"e_1_3_3_2_16_2","unstructured":"Xiang Deng Yu Gu Boyuan Zheng Shijie Chen Sam Stevens Boshi Wang Huan Sun and Yu Su. 2024. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Giuseppe Desolda Carmelo Ardito Maria\u00a0Francesca Costabile and Maristella Matera. 2017. End-user composition of interactive applications through actionable UI components. Journal of Visual Languages & Computing 42 (2017) 46\u201359.","DOI":"10.1016\/j.jvlc.2017.08.004"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2481492.2481500"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753554"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523711"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702551"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Diego Firmenich Sergio Firmenich Jos\u00e9\u00a0Mat\u00edas Rivero Leandro Antonelli and Gustavo Rossi. 2018. CrowdMock: an approach for defining and evolving web augmentation requirements. Requirements Engineering 23 (2018) 33\u201361.","DOI":"10.1007\/s00766-016-0257-3"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Giuseppe Ghiani Fabio Patern\u00f2 Lucio\u00a0Davide Spano and Giuliano Pintori. 2016. An environment for end-user development of web mashups. International Journal of Human-Computer Studies 87 (2016) 38\u201364.","DOI":"10.1016\/j.ijhcs.2015.10.008"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1943403.1943439"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1166253.1166257"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376804"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357203"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1166253.1166274"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Bo Jiang Pengxiang Liu Ye Wang and Yezhi Chen. 2020. HyOASAM: A hybrid open API selection approach for mashup development. Mathematical Problems in Engineering 2020 1 (2020) 4984375.","DOI":"10.1155\/2020\/4984375"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481415"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/VL\/HCC51201.2021.9576476"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/VL\/HCC53370.2022.9833005"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/VL\/HCC60511.2024.00040"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675166"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/VL.1995.520818"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Tessa Lau. 2009. Why Programming by Demonstration Systems Fail: Lessons Learned for Usable AI. AI Magazine 30 4 (2009) 65\u201367.","DOI":"10.1609\/aimag.v30i4.2262"},{"key":"e_1_3_3_2_38_2","first-page":"18893","volume-title":"International Conference on Machine Learning","author":"Lee Kenton","year":"2023","unstructured":"Kenton Lee, Mandar Joshi, Iulia\u00a0Raluca Turc, Hexiang Hu, Fangyu Liu, Julian\u00a0Martin Eisenschlos, Urvashi Khandelwal, Peter Shaw, Ming-Wei Chang, and Kristina Toutanova. 2023. Pix2struct: Screenshot parsing as pretraining for visual language understanding. In International Conference on Machine Learning. PMLR, 18893\u201318912."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Tak\u00a0Yeon Lee and Benjamin\u00a0B Bederson. 2016. Give the people what they want: studying end-user needs for enhancing the web. PeerJ Computer Science 2 (2016) e91.","DOI":"10.7717\/peerj-cs.91"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357323"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025483"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-5386-X_1"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/1502650.1502667"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642149"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Jos\u00e9\u00a0A Mac\u00edas and Fabio Patern\u00f2. 2008. Customization of Web applications through an intelligent environment exploiting logical interface descriptions. Interacting with Computers 20 1 (2008) 29\u201347.","DOI":"10.1016\/j.intcom.2007.07.007"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Daniele Massa and Lucio\u00a0Davide Spano. 2016. Facemashup: An end-user development tool for social network data. Future Internet 8 2 (2016) 10.","DOI":"10.3390\/fi8020010"},{"key":"e_1_3_3_2_47_2","unstructured":"Microsoft. 2023. Reinventing Search with a New AI-Powered Microsoft Bing and Edge Your Copilot for the Web. https:\/\/blogs.microsoft.com\/blog\/2023\/02\/07\/reinventing-search-with-a-new-ai-powered-microsoft-bing-and-edge-your-copilot-for-the-web\/. Accessed: September 2024."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985700"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.5555\/647055.715910"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/506443.506447"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/502716.502734"},{"key":"e_1_3_3_2_52_2","unstructured":"Ottogrid.ai. 2024. AI-Powered Automation for Manual Research. https:\/\/ottogrid.ai\/. Accessed: September 2024."},{"key":"e_1_3_3_2_53_2","unstructured":"Rabbit Research Team. 2023. Learning Human Actions on Computer Applications. https:\/\/www.rabbit.tech\/research. Accessed: September 2024."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/1502650.1502676"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377515"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Nigel Shadbolt Tim Berners-Lee and Wendy Hall. 2006. The semantic web revisited. IEEE intelligent systems 21 3 (2006) 96\u2013101.","DOI":"10.1109\/MIS.2006.62"},{"key":"e_1_3_3_2_57_2","unstructured":"Michael Spahn Christian Dorner and Volker Wulf. 2008. End user development: approaches towards a flexible software design. (2008)."},{"key":"e_1_3_3_2_58_2","series-title":"(GI \u201909)","first-page":"215","volume-title":"Proceedings of Graphics Interface 2009","author":"Su Sara\u00a0L.","year":"2009","unstructured":"Sara\u00a0L. Su, Sylvain Paris, and Fr\u00e9do Durand. 2009. QuickSelect: history-based selection expansion. In Proceedings of Graphics Interface 2009 (Kelowna, British Columbia, Canada) (GI \u201909). Canadian Information Processing Society, CAN, 215\u2013221."},{"key":"e_1_3_3_2_59_2","unstructured":"Taxy AI. 2024. Automate Your Browser with GPT-4. https:\/\/taxy.ai\/. Accessed: September 2024."},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Tom Veuskens Kris Luyten and Raf Ramakers. 2020. Rataplan: Resilient automation of user interface actions with multi-modal proxies. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 4 2 (2020) 1\u201323.","DOI":"10.1145\/3397329"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563835.3567663"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581525"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240842"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606824"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474763"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74800-7_46"},{"key":"e_1_3_3_2_67_2","unstructured":"Boyuan Zheng Boyu Gou Jihyung Kil Huan Sun and Yu Su. 2024. Gpt-4v (ision) is a generalist web agent if grounded. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.01614 (2024)."}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Busan Republic of Korea","acronym":"UIST '25"},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:05:01Z","timestamp":1759010701000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747780"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":66,"alternative-id":["10.1145\/3746059.3747780","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747780","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}