% AwesomeCUA: {"catalog_id": "arxiv:1602.02261", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "1602.02261"}} @misc{arxiv_1602_02261, title = {{End-to-End Goal-Driven Web Navigation}}, author = {{Rodrigo Nogueira} and {Kyunghyun Cho}}, year = {2016}, eprint = {1602.02261v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1602.02261v2}, note = {First published: 2016-02-06; Recorded arXiv version: v2; Recorded version updated: 2016-05-20T16:26:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:1802.08802", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "1802.08802"}} @misc{arxiv_1802_08802, title = {{Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration}}, author = {{Evan Zheran Liu} and {Kelvin Guu} and {Panupong Pasupat} and {Tianlin Shi} and {Percy Liang}}, year = {2018}, eprint = {1802.08802v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1802.08802v1}, note = {First published: 2018-02-24; Recorded arXiv version: v1; Recorded version updated: 2018-02-24T05:32:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:1808.09132", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "1808.09132"}} @misc{arxiv_1808_09132, title = {{Mapping Natural Language Commands to Web Elements}}, author = {{Panupong Pasupat} and {Tian-Shun Jiang} and {Evan Zheran Liu} and {Kelvin Guu} and {Percy Liang}}, year = {2018}, eprint = {1808.09132v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1808.09132v2}, note = {First published: 2018-08-28; Recorded arXiv version: v2; Recorded version updated: 2018-10-01T03:22:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:1909.00031", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "1909.00031"}} @misc{arxiv_1909_00031, title = {{Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrations}}, author = {{Toby Jia-Jun Li} and {Marissa Radensky} and {Justin Jia} and {Kirielle Singarajah} and {Tom M. Mitchell} and {Brad A. Myers}}, year = {2019}, eprint = {1909.00031v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1909.00031v2}, note = {First published: 2019-08-30; Recorded arXiv version: v2; Recorded version updated: 2020-01-07T00:57:53Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2005.03776", "catalog_id": "arxiv:2005.03776", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2005.03776"}, "publication": {"authors": ["Yang Li", "Jiacong He", "Xin Zhou", "Yuan Zhang", "Jason Baldridge"], "date_basis": "Explicit publisher metadata: 2020/7; precision=month.", "date_parts": [2020, 7], "doi": "10.18653/v1/2020.acl-main.729", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2020.acl-main.729/"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "8198-8210", "pdf_url": "https://aclanthology.org/2020.acl-main.729.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Mapping Natural Language Instructions to Mobile UI Action Sequences", "type": "conference-paper", "url": "https://aclanthology.org/2020.acl-main.729/", "venue": "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", "volume": null}} @misc{arxiv_2005_03776, title = {{Mapping Natural Language Instructions to Mobile UI Action Sequences}}, author = {{Yang Li} and {Jiacong He} and {Xin Zhou} and {Yuan Zhang} and {Jason Baldridge}}, year = {2020}, eprint = {2005.03776v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2005.03776v2}, note = {First published: 2020-05-07; Recorded arXiv version: v2; Recorded version updated: 2020-06-05T02:11:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2008.05132", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2008.05132"}} @misc{arxiv_2008_05132, title = {{Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?}}, author = {{Jieshan Chen} and {Mulong Xie} and {Zhenchang Xing} and {Chunyang Chen} and {Xiwei Xu} and {Liming Zhu} and {Guoqiang Li}}, year = {2020}, eprint = {2008.05132v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2008.05132v2}, note = {First published: 2020-08-12; Recorded arXiv version: v2; Recorded version updated: 2020-09-07T12:57:33Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2010.04295", "catalog_id": "arxiv:2010.04295", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2010.04295"}, "publication": {"authors": ["Yang Li", "Gang Li", "Luheng He", "Jingjie Zheng", "Hong Li", "Zhiwei Guan"], "date_basis": "Explicit publisher metadata: 2020/11; precision=month.", "date_parts": [2020, 11], "doi": "10.18653/v1/2020.emnlp-main.443", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2020.emnlp-main.443/"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The retained arXiv abstract reports 162,859 phrases; the ACL abstract reports 162,860. This publication proposal does not overwrite the arXiv annotation or assert a unified dataset count. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "5495-5510", "pdf_url": "https://aclanthology.org/2020.emnlp-main.443.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements", "type": "conference-paper", "url": "https://aclanthology.org/2020.emnlp-main.443/", "venue": "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", "volume": null}} @misc{arxiv_2010_04295, title = {{Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements}}, author = {{Yang Li} and {Gang Li} and {Luheng He} and {Jingjie Zheng} and {Hong Li} and {Zhiwei Guan}}, year = {2020}, eprint = {2010.04295v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2010.04295v1}, note = {First published: 2020-10-08; Recorded arXiv version: v1; Recorded version updated: 2020-10-08T22:56:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2012.12350", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2012.12350"}} @misc{arxiv_2012_12350, title = {{ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces}}, author = {{Zecheng He} and {Srinivas Sunkara} and {Xiaoxue Zang} and {Ying Xu} and {Lijuan Liu} and {Nevan Wichers} and {Gabriel Schubiner} and {Ruby Lee} and {Jindong Chen} and {Blaise Agüera y Arcas}}, year = {2020}, eprint = {2012.12350v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2012.12350v2}, note = {First published: 2020-12-22; Recorded arXiv version: v2; Recorded version updated: 2021-01-25T20:37:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2101.04893", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2101.04893"}} @misc{arxiv_2101_04893, title = {{Screen Recognition: Creating Accessibility Metadata for Mobile Applications from Pixels}}, author = {{Xiaoyi Zhang} and {Lilian de Greef} and {Amanda Swearngin} and {Samuel White} and {Kyle Murray} and {Lisa Yu} and {Qi Shan} and {Jeffrey Nichols} and {Jason Wu} and {Chris Fleizach} and {Aaron Everitt} and {Jeffrey P. Bigham}}, year = {2021}, eprint = {2101.04893v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2101.04893v1}, note = {First published: 2021-01-13; Recorded arXiv version: v1; Recorded version updated: 2021-01-13T05:56:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2101.09465", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2101.09465"}} @misc{arxiv_2101_09465, title = {{WebSRC: A Dataset for Web-Based Structural Reading Comprehension}}, author = {{Xingyu Chen} and {Zihan Zhao} and {Lu Chen} and {Danyang Zhang} and {Jiabao Ji} and {Ao Luo} and {Yuxuan Xiong} and {Kai Yu}}, year = {2021}, eprint = {2101.09465v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2101.09465v2}, note = {First published: 2021-01-23; Recorded arXiv version: v2; Recorded version updated: 2021-11-08T08:31:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2103.16057", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2103.16057"}} @misc{arxiv_2103_16057, title = {{Grounding Open-Domain Instructions to Automate Web Support Tasks}}, author = {{Nancy Xu} and {Sam Masling} and {Michael Du} and {Giovanni Campagna} and {Larry Heck} and {James Landay} and {Monica S Lam}}, year = {2021}, eprint = {2103.16057v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2103.16057v2}, note = {First published: 2021-03-30; Recorded arXiv version: v2; Recorded version updated: 2021-04-04T23:51:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2105.11941", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2105.11941"}} @misc{arxiv_2105_11941, title = {{Understanding Mobile GUI: from Pixel-Words to Screen-Sentences}}, author = {{Jingwen Fu} and {Xiaoyi Zhang} and {Yuwang Wang} and {Wenjun Zeng} and {Sam Yang} and {Grayson Hilliard}}, year = {2021}, eprint = {2105.11941v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2105.11941v2}, note = {First published: 2021-05-25; Recorded arXiv version: v2; Recorded version updated: 2022-04-14T11:00:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2105.13231", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2105.13231"}} @misc{arxiv_2105_13231, title = {{AndroidEnv: A Reinforcement Learning Platform for Android}}, author = {{Daniel Toyama} and {Philippe Hamel} and {Anita Gergely} and {Gheorghe Comanici} and {Amelia Glaese} and {Zafarali Ahmed} and {Tyler Jackson} and {Shibl Mourad} and {Doina Precup}}, year = {2021}, eprint = {2105.13231v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2105.13231v1}, note = {First published: 2021-05-27; Recorded arXiv version: v1; Recorded version updated: 2021-05-27T15:20:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2107.13731", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2107.13731"}} @misc{arxiv_2107_13731, title = {{UIBert: Learning Generic Multimodal Representations for UI Understanding}}, author = {{Chongyang Bai} and {Xiaoxue Zang} and {Ying Xu} and {Srinivas Sunkara} and {Abhinav Rastogi} and {Jindong Chen} and {Blaise Aguera y Arcas}}, year = {2021}, eprint = {2107.13731v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2107.13731v2}, note = {First published: 2021-07-29; Recorded arXiv version: v2; Recorded version updated: 2021-08-10T08:55:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2108.03353", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2108.03353"}} @misc{arxiv_2108_03353, title = {{Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning}}, author = {{Bryan Wang} and {Gang Li} and {Xin Zhou} and {Zhourong Chen} and {Tovi Grossman} and {Yang Li}}, year = {2021}, eprint = {2108.03353v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2108.03353v1}, note = {First published: 2021-08-07; Recorded arXiv version: v1; Recorded version updated: 2021-08-07T03:01:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2112.05692", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2112.05692"}} @misc{arxiv_2112_05692, title = {{VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling}}, author = {{Yang Li} and {Gang Li} and {Xin Zhou} and {Mostafa Dehghani} and {Alexey Gritsenko}}, year = {2021}, eprint = {2112.05692v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2112.05692v1}, note = {First published: 2021-12-10; Recorded arXiv version: v1; Recorded version updated: 2021-12-10T17:37:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2201.04100", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2201.04100"}} @misc{arxiv_2201_04100, title = {{Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale}}, author = {{Gang Li} and {Gilles Baechler} and {Manuel Tragut} and {Yang Li}}, year = {2022}, eprint = {2201.04100v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2201.04100v2}, note = {First published: 2022-01-11; Recorded arXiv version: v2; Recorded version updated: 2022-01-13T17:53:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2202.02312", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2202.02312"}} @misc{arxiv_2202_02312, title = {{A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility}}, author = {{Andrea Burns} and {Deniz Arsan} and {Sanjna Agrawal} and {Ranjitha Kumar} and {Kate Saenko} and {Bryan A. Plummer}}, year = {2022}, eprint = {2202.02312v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2202.02312v3}, note = {First published: 2022-02-04; Recorded arXiv version: v3; Recorded version updated: 2022-08-15T00:24:24Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2202.08137", "catalog_id": "arxiv:2202.08137", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2202.08137"}, "publication": {"authors": ["Peter Humphreys", "David Raposo", "Toby Pohlen", "Gregory Thornton", "Rachita Chhaparia", "Alistair Muldal", "Josh Abramson", "Petko Georgiev", "Adam Santoro", "Timothy Lillicrap"], "date_basis": "Explicit publisher metadata: 2022/06/28; precision=day.", "date_parts": [2022, 6, 28], "doi": null, "event_dates": "17--23 Jul 2022", "evidence_urls": ["https://proceedings.mlr.press/v162/humphreys22a.html", "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The formal ICML PDF lists 10 authors beginning Peter Humphreys and uses Toby Pohlen. The landing lists Peter C Humphreys and Tobias Pohlen. The retained arXiv snapshot lists 11 authors, including Alex Goldin. These are preserved as distinct version-specific author lists; the publication field uses only the formal PDF list. The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher issue date is 2022-06-28; the July 17\u201323 conference range is an event date, not a substitute publication day. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "9466-9482", "pdf_url": "https://proceedings.mlr.press/v162/humphreys22a/humphreys22a.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "A Data-Driven Approach for Learning to Control Computers", "type": "conference-paper", "url": "https://proceedings.mlr.press/v162/humphreys22a.html", "venue": "Proceedings of the 39th International Conference on Machine Learning", "volume": "162"}} @misc{arxiv_2202_08137, title = {{A data-driven approach for learning to control computers}}, author = {{Peter C Humphreys} and {David Raposo} and {Toby Pohlen} and {Gregory Thornton} and {Rachita Chhaparia} and {Alistair Muldal} and {Josh Abramson} and {Petko Georgiev} and {Alex Goldin} and {Adam Santoro} and {Timothy Lillicrap}}, year = {2022}, eprint = {2202.08137v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2202.08137v2}, note = {First published: 2022-02-16; Recorded arXiv version: v2; Recorded version updated: 2022-11-11T13:45:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2205.11029", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2205.11029"}} @misc{arxiv_2205_11029, title = {{META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI}}, author = {{Liangtai Sun} and {Xingyu Chen} and {Lu Chen} and {Tianle Dai} and {Zichen Zhu} and {Kai Yu}}, year = {2022}, eprint = {2205.11029v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2205.11029v2}, note = {First published: 2022-05-23; Recorded arXiv version: v2; Recorded version updated: 2022-11-24T06:34:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2207.01206", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2207.01206"}} @misc{arxiv_2207_01206, title = {{WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents}}, author = {{Shunyu Yao} and {Howard Chen} and {John Yang} and {Karthik Narasimhan}}, year = {2022}, eprint = {2207.01206v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2207.01206v4}, note = {First published: 2022-07-04; Recorded arXiv version: v4; Recorded version updated: 2023-02-08T01:39:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2209.08199", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2209.08199"}} @misc{arxiv_2209_08199, title = {{ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots}}, author = {{Yu-Chung Hsiao} and {Fedir Zubach} and {Gilles Baechler} and {Srinivas Sunkara} and {Victor Carbune} and {Jason Lin} and {Maria Wang} and {Yun Zhu} and {Jindong Chen}}, year = {2022}, eprint = {2209.08199v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2209.08199v4}, note = {First published: 2022-09-16; Recorded arXiv version: v4; Recorded version updated: 2025-02-09T21:09:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2209.08655", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2209.08655"}} @misc{arxiv_2209_08655, title = {{Enabling Conversational Interaction with Mobile UI using Large Language Models}}, author = {{Bryan Wang} and {Gang Li} and {Yang Li}}, year = {2022}, eprint = {2209.08655v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2209.08655v2}, note = {First published: 2022-09-18; Recorded arXiv version: v2; Recorded version updated: 2023-02-17T21:24:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2209.14927", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2209.14927"}} @misc{arxiv_2209_14927, title = {{Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus}}, author = {{Gang Li} and {Yang Li}}, year = {2022}, eprint = {2209.14927v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2209.14927v4}, note = {First published: 2022-09-29; Recorded arXiv version: v4; Recorded version updated: 2023-02-24T01:41:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2209.15099", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2209.15099"}} @misc{arxiv_2209_15099, title = {{MUG: Interactive Multimodal Grounding on User Interfaces}}, author = {{Tao Li} and {Gang Li} and {Jingjie Zheng} and {Purple Wang} and {Yang Li}}, year = {2022}, eprint = {2209.15099v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2209.15099v1}, note = {First published: 2022-09-29; Recorded arXiv version: v1; Recorded version updated: 2022-09-29T21:08:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2210.02663", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2210.02663"}} @misc{arxiv_2210_02663, title = {{Towards Better Semantic Understanding of Mobile Interfaces}}, author = {{Srinivas Sunkara} and {Maria Wang} and {Lijuan Liu} and {Gilles Baechler} and {Yu-Chung Hsiao} and {Jindong} and {Chen} and {Abhanshu Sharma} and {James Stout}}, year = {2022}, eprint = {2210.02663v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.02663v1}, note = {First published: 2022-10-06; Recorded arXiv version: v1; Recorded version updated: 2022-10-06T03:48:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2210.03347", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2210.03347"}} @misc{arxiv_2210_03347, title = {{Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding}}, author = {{Kenton Lee} and {Mandar Joshi} and {Iulia Turc} and {Hexiang Hu} and {Fangyu Liu} and {Julian Eisenschlos} and {Urvashi Khandelwal} and {Peter Shaw} and {Ming-Wei Chang} and {Kristina Toutanova}}, year = {2022}, eprint = {2210.03347v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.03347v2}, note = {First published: 2022-10-07; Recorded arXiv version: v2; Recorded version updated: 2023-06-15T21:34:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2210.03945", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2210.03945"}} @misc{arxiv_2210_03945, title = {{Understanding HTML with Large Language Models}}, author = {{Izzeddin Gur} and {Ofir Nachum} and {Yingjie Miao} and {Mustafa Safdari} and {Austin Huang} and {Aakanksha Chowdhery} and {Sharan Narang} and {Noah Fiedel} and {Aleksandra Faust}}, year = {2022}, eprint = {2210.03945v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.03945v2}, note = {First published: 2022-10-08; Recorded arXiv version: v2; Recorded version updated: 2023-05-19T17:42:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2211.07615", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2211.07615"}} @misc{arxiv_2211_07615, title = {{UGIF: UI Grounded Instruction Following}}, author = {{Sagar Gubbi Venkatesh} and {Partha Talukdar} and {Srini Narayanan}}, year = {2022}, eprint = {2211.07615v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2211.07615v2}, note = {First published: 2022-11-14; Recorded arXiv version: v2; Recorded version updated: 2023-05-23T16:08:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2301.10165", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2301.10165"}} @misc{arxiv_2301_10165, title = {{Lexi: Self-Supervised Learning of the UI Language}}, author = {{Pratyay Banerjee} and {Shweti Mahajan} and {Kushal Arora} and {Chitta Baral} and {Oriana Riva}}, year = {2023}, eprint = {2301.10165v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2301.10165v1}, note = {First published: 2023-01-23; Recorded arXiv version: v1; Recorded version updated: 2023-01-23T09:05:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2301.13280", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2301.13280"}} @misc{arxiv_2301_13280, title = {{WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics}}, author = {{Jason Wu} and {Siyan Wang} and {Siman Shen} and {Yi-Hao Peng} and {Jeffrey Nichols} and {Jeffrey P. Bigham}}, year = {2023}, eprint = {2301.13280v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2301.13280v1}, note = {First published: 2023-01-30; Recorded arXiv version: v1; Recorded version updated: 2023-01-30T20:47:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2303.17491", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2303.17491"}} @misc{arxiv_2303_17491, title = {{Language Models can Solve Computer Tasks}}, author = {{Geunwoo Kim} and {Pierre Baldi} and {Stephen McAleer}}, year = {2023}, eprint = {2303.17491v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2303.17491v3}, note = {First published: 2023-03-30; Recorded arXiv version: v3; Recorded version updated: 2023-11-16T20:15:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2304.07061", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2304.07061"}} @misc{arxiv_2304_07061, title = {{DroidBot-GPT: GPT-powered UI Automation for Android}}, author = {{Hao Wen} and {Hongming Wang} and {Jiaxuan Liu} and {Yuanchun Li}}, year = {2023}, eprint = {2304.07061v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2304.07061v5}, note = {First published: 2023-04-14; Recorded arXiv version: v5; Recorded version updated: 2024-01-07T08:23:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2305.08144", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2305.08144"}} @misc{arxiv_2305_08144, title = {{Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction}}, author = {{Danyang Zhang} and {Zhennan Shen} and {Rui Xie} and {Situo Zhang} and {Tianbao Xie} and {Zihan Zhao} and {Siyuan Chen} and {Lu Chen} and {Hongshen Xu} and {Ruisheng Cao} and {Kai Yu}}, year = {2023}, eprint = {2305.08144v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.08144v4}, note = {First published: 2023-05-14; Recorded arXiv version: v4; Recorded version updated: 2024-06-13T11:51:37Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2305.11854", "catalog_id": "arxiv:2305.11854", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2305.11854"}, "publication": {"authors": ["Hiroki Furuta", "Kuang-Huei Lee", "Ofir Nachum", "Yutaka Matsuo", "Aleksandra Faust", "Shixiang Shane Gu", "Izzeddin Gur"], "date_basis": "Explicit publisher metadata: 2024-05-31; precision=day.", "date_parts": [2024, 5, 31], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2024/hash/7ef7d8359036afd8c2378d82c21058a4-Abstract-Conference.html", "https://proceedings.iclr.cc/paper_files/paper/2024/file/7ef7d8359036afd8c2378d82c21058a4-Paper-Conference.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The ICLR landing shortens Shixiang Shane Gu to Shixiang Gu. Publication authors use the full PDF title-page form. Volume 2024 and pages 29528\u201329558 are explicit publisher citation metadata, not values inferred from the event year or PDF page count. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "29528-29558", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2024/file/7ef7d8359036afd8c2378d82c21058a4-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Multimodal Web Navigation with Instruction-Finetuned Foundation Models", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/7ef7d8359036afd8c2378d82c21058a4-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2024"}} @misc{arxiv_2305_11854, title = {{Multimodal Web Navigation with Instruction-Finetuned Foundation Models}}, author = {{Hiroki Furuta} and {Kuang-Huei Lee} and {Ofir Nachum} and {Yutaka Matsuo} and {Aleksandra Faust} and {Shixiang Shane Gu} and {Izzeddin Gur}}, year = {2023}, eprint = {2305.11854v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.11854v4}, note = {First published: 2023-05-19; Recorded arXiv version: v4; Recorded version updated: 2024-02-25T16:21:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2305.14257", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2305.14257"}} @misc{arxiv_2305_14257, title = {{Hierarchical Prompting Assists Large Language Model on Web Navigation}}, author = {{Abishek Sridhar} and {Robert Lo} and {Frank F. Xu} and {Hao Zhu} and {Shuyan Zhou}}, year = {2023}, eprint = {2305.14257v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.14257v3}, note = {First published: 2023-05-23; Recorded arXiv version: v3; Recorded version updated: 2023-10-30T00:55:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2305.16653", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2305.16653"}} @misc{arxiv_2305_16653, title = {{AdaPlanner: Adaptive Planning from Feedback with Language Models}}, author = {{Haotian Sun} and {Yuchen Zhuang} and {Lingkai Kong} and {Bo Dai} and {Chao Zhang}}, year = {2023}, eprint = {2305.16653v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.16653v1}, note = {First published: 2023-05-26; Recorded arXiv version: v1; Recorded version updated: 2023-05-26T05:52:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2305.19308", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2305.19308"}} @misc{arxiv_2305_19308, title = {{SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models}}, author = {{Hongxin Li} and {Jingran Su} and {Yuntao Chen} and {Qing Li} and {Zhaoxiang Zhang}}, year = {2023}, eprint = {2305.19308v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.19308v2}, note = {First published: 2023-05-30; Recorded arXiv version: v2; Recorded version updated: 2023-10-30T06:36:24Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2306.00245", "catalog_id": "arxiv:2306.00245", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2306.00245"}, "publication": {"authors": ["Peter Shaw", "Mandar Joshi", "James Cohan", "Jonathan Berant", "Panupong Pasupat", "Hexiang Hu", "Urvashi Khandelwal", "Kenton Lee", "Kristina Toutanova"], "date_basis": "Explicit publisher metadata: 2023-12-15; precision=day.", "date_parts": [2023, 12, 15], "doi": "10.52202/075280-1490", "event_dates": null, "evidence_urls": ["https://papers.nips.cc/paper_files/paper/2023/hash/6c52a8a4fadc9129c6e1d1745f2dfd0f-Abstract-Conference.html", "https://proceedings.neurips.cc/paper_files/paper/2023/file/6c52a8a4fadc9129c6e1d1745f2dfd0f-Paper-Conference.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The NeurIPS landing metadata adds the initial N to Kristina Toutanova; the formal paper title page does not. Publication authors use the PDF. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "34354-34370", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/6c52a8a4fadc9129c6e1d1745f2dfd0f-Paper-Conference.pdf", "publisher": null, "series": null, "title": "From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces", "type": "conference-paper", "url": "https://papers.nips.cc/paper_files/paper/2023/hash/6c52a8a4fadc9129c6e1d1745f2dfd0f-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36"}} @misc{arxiv_2306_00245, title = {{From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces}}, author = {{Peter Shaw} and {Mandar Joshi} and {James Cohan} and {Jonathan Berant} and {Panupong Pasupat} and {Hexiang Hu} and {Urvashi Khandelwal} and {Kenton Lee} and {Kristina Toutanova}}, year = {2023}, eprint = {2306.00245v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.00245v2}, note = {First published: 2023-05-31; Recorded arXiv version: v2; Recorded version updated: 2023-12-06T23:46:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2306.01242", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2306.01242"}} @misc{arxiv_2306_01242, title = {{Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators}}, author = {{Zhizheng Zhang} and {Xiaoyi Zhang} and {Wenxuan Xie} and {Yan Lu}}, year = {2023}, eprint = {2306.01242v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.01242v2}, note = {First published: 2023-06-02; Recorded arXiv version: v2; Recorded version updated: 2023-12-04T13:36:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2306.06070", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2306.06070"}} @misc{arxiv_2306_06070, title = {{Mind2Web: Towards a Generalist Agent for the Web}}, author = {{Xiang Deng} and {Yu Gu} and {Boyuan Zheng} and {Shijie Chen} and {Samuel Stevens} and {Boshi Wang} and {Huan Sun} and {Yu Su}}, year = {2023}, eprint = {2306.06070v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.06070v3}, note = {First published: 2023-06-09; Recorded arXiv version: v3; Recorded version updated: 2023-12-09T05:57:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2306.07863", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2306.07863"}} @misc{arxiv_2306_07863, title = {{Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control}}, author = {{Longtao Zheng} and {Rundong Wang} and {Xinrun Wang} and {Bo An}}, year = {2023}, eprint = {2306.07863v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.07863v3}, note = {First published: 2023-06-13; Recorded arXiv version: v3; Recorded version updated: 2024-01-19T06:59:26Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2307.10088", "catalog_id": "arxiv:2307.10088", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2307.10088"}, "publication": {"authors": ["Christopher Rawles", "Alice Li", "Daniel Rodriguez", "Oriana Riva", "Timothy Lillicrap"], "date_basis": "Explicit publisher citation_publication_date: 2023-12-15. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2023, 12, 15], "doi": "10.52202/075280-2609", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "59708-59728", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2023/file/bbbb6308b402fe909c39dd29950c32e0-Paper-Datasets_and_Benchmarks.pdf", "publisher": null, "series": null, "title": "AndroidInTheWild: A Large-Scale Dataset For Android Device Control", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/bbbb6308b402fe909c39dd29950c32e0-Abstract-Datasets_and_Benchmarks.html", "venue": "Advances in Neural Information Processing Systems", "volume": "36"}} @misc{arxiv_2307_10088, title = {{Android in the Wild: A Large-Scale Dataset for Android Device Control}}, author = {{Christopher Rawles} and {Alice Li} and {Daniel Rodriguez} and {Oriana Riva} and {Timothy Lillicrap}}, year = {2023}, eprint = {2307.10088v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2307.10088v2}, note = {First published: 2023-07-19; Recorded arXiv version: v2; Recorded version updated: 2023-10-27T14:24:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2307.12856", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2307.12856"}} @misc{arxiv_2307_12856, title = {{A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis}}, author = {{Izzeddin Gur} and {Hiroki Furuta} and {Austin Huang} and {Mustafa Safdari} and {Yutaka Matsuo} and {Douglas Eck} and {Aleksandra Faust}}, year = {2023}, eprint = {2307.12856v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2307.12856v4}, note = {First published: 2023-07-24; Recorded arXiv version: v4; Recorded version updated: 2024-02-25T16:17:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2307.13854", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2307.13854"}} @misc{arxiv_2307_13854, title = {{WebArena: A Realistic Web Environment for Building Autonomous Agents}}, author = {{Shuyan Zhou} and {Frank F. Xu} and {Hao Zhu} and {Xuhui Zhou} and {Robert Lo} and {Abishek Sridhar} and {Xianyi Cheng} and {Tianyue Ou} and {Yonatan Bisk} and {Daniel Fried} and {Uri Alon} and {Graham Neubig}}, year = {2023}, eprint = {2307.13854v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2307.13854v4}, note = {First published: 2023-07-25; Recorded arXiv version: v4; Recorded version updated: 2024-04-16T15:13:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2308.03688", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2308.03688"}} @misc{arxiv_2308_03688, title = {{AgentBench: Evaluating LLMs as Agents}}, author = {{Xiao Liu} and {Hao Yu} and {Hanchen Zhang} and {Yifan Xu} and {Xuanyu Lei} and {Hanyu Lai} and {Yu Gu} and {Hangliang Ding} and {Kaiwen Men} and {Kejuan Yang} and {Shudan Zhang} and {Xiang Deng} and {Aohan Zeng} and {Zhengxiao Du} and {Chenhui Zhang} and {Sheng Shen} and {Tianjun Zhang} and {Yu Su} and {Huan Sun} and {Minlie Huang} and {Yuxiao Dong} and {Jie Tang}}, year = {2023}, eprint = {2308.03688v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.03688v3}, note = {First published: 2023-08-07; Recorded arXiv version: v3; Recorded version updated: 2025-10-04T03:54:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2308.15272", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2308.15272"}} @misc{arxiv_2308_15272, title = {{AutoDroid: LLM-powered Task Automation in Android}}, author = {{Hao Wen} and {Yuanchun Li} and {Guohong Liu} and {Shanhui Zhao} and {Tao Yu} and {Toby Jia-Jun Li} and {Shiqi Jiang} and {Yunhao Liu} and {Yaqin Zhang} and {Yunxin Liu}}, year = {2023}, eprint = {2308.15272v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.15272v4}, note = {First published: 2023-08-29; Recorded arXiv version: v4; Recorded version updated: 2024-03-09T09:38:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2309.08172", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2309.08172"}} @misc{arxiv_2309_08172, title = {{LASER: LLM Agent with State-Space Exploration for Web Navigation}}, author = {{Kaixin Ma} and {Hongming Zhang} and {Hongwei Wang} and {Xiaoman Pan} and {Wenhao Yu} and {Dong Yu}}, year = {2023}, eprint = {2309.08172v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2309.08172v2}, note = {First published: 2023-09-15; Recorded arXiv version: v2; Recorded version updated: 2024-02-21T17:42:32Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2309.11436", "catalog_id": "arxiv:2309.11436", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2309.11436"}, "publication": {"authors": ["Zhuosheng Zhang", "Aston Zhang"], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.findings-acl.186", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-acl.186/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "3132-3149", "pdf_url": "https://aclanthology.org/2024.findings-acl.186.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "You Only Look at Screens: Multimodal Chain-of-Action Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-acl.186/", "venue": "Findings of the Association for Computational Linguistics: ACL 2024", "volume": null}} @misc{arxiv_2309_11436, title = {{You Only Look at Screens: Multimodal Chain-of-Action Agents}}, author = {{Zhuosheng Zhang} and {Aston Zhang}}, year = {2023}, eprint = {2309.11436v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2309.11436v4}, note = {First published: 2023-09-20; Recorded arXiv version: v4; Recorded version updated: 2024-06-07T04:52:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.03720", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2310.03720"}} @misc{arxiv_2310_03720, title = {{SteP: Stacked LLM Policies for Web Actions}}, author = {{Paloma Sodhi} and {S. R. K. Branavan} and {Yoav Artzi} and {Ryan McDonald}}, year = {2023}, eprint = {2310.03720v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.03720v4}, note = {First published: 2023-10-05; Recorded arXiv version: v4; Recorded version updated: 2024-08-08T18:00:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.04716", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2310.04716"}} @misc{arxiv_2310_04716, title = {{Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API}}, author = {{Zhizheng Zhang} and {Wenxuan Xie} and {Xiaoyi Zhang} and {Yan Lu}}, year = {2023}, eprint = {2310.04716v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.04716v1}, note = {First published: 2023-10-07; Recorded arXiv version: v1; Recorded version updated: 2023-10-07T07:22:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.04869", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2310.04869"}} @misc{arxiv_2310_04869, title = {{ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations}}, author = {{Yue Jiang} and {Eldon Schoop} and {Amanda Swearngin} and {Jeffrey Nichols}}, year = {2023}, eprint = {2310.04869v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.04869v1}, note = {First published: 2023-10-07; Recorded arXiv version: v1; Recorded version updated: 2023-10-07T16:32:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.05126", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2310.05126"}} @misc{arxiv_2310_05126, title = {{UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model}}, author = {{Jiabo Ye} and {Anwen Hu} and {Haiyang Xu} and {Qinghao Ye} and {Ming Yan} and {Guohai Xu} and {Chenliang Li} and {Junfeng Tian} and {Qi Qian} and {Ji Zhang} and {Qin Jin} and {Liang He} and {Xin Alex Lin} and {Fei Huang}}, year = {2023}, eprint = {2310.05126v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.05126v1}, note = {First published: 2023-10-08; Recorded arXiv version: v1; Recorded version updated: 2023-10-08T11:33:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.08740", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2310.08740"}} @misc{arxiv_2310_08740, title = {{A Zero-Shot Language Agent for Computer Control with Structured Reflection}}, author = {{Tao Li} and {Gang Li} and {Zhiwei Deng} and {Bryan Wang} and {Yang Li}}, year = {2023}, eprint = {2310.08740v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.08740v3}, note = {First published: 2023-10-12; Recorded arXiv version: v3; Recorded version updated: 2023-10-23T17:39:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.10634", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2310.10634"}} @misc{arxiv_2310_10634, title = {{OpenAgents: An Open Platform for Language Agents in the Wild}}, author = {{Tianbao Xie} and {Fan Zhou} and {Zhoujun Cheng} and {Peng Shi} and {Luoxuan Weng} and {Yitao Liu} and {Toh Jing Hua} and {Junning Zhao} and {Qian Liu} and {Che Liu} and {Leo Z. Liu} and {Yiheng Xu} and {Hongjin Su} and {Dongchan Shin} and {Caiming Xiong} and {Tao Yu}}, year = {2023}, eprint = {2310.10634v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.10634v1}, note = {First published: 2023-10-16; Recorded arXiv version: v1; Recorded version updated: 2023-10-16T17:54:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.11441", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2310.11441"}} @misc{arxiv_2310_11441, title = {{Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V}}, author = {{Jianwei Yang} and {Hao Zhang} and {Feng Li} and {Xueyan Zou} and {Chunyuan Li} and {Jianfeng Gao}}, year = {2023}, eprint = {2310.11441v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.11441v2}, note = {First published: 2023-10-17; Recorded arXiv version: v2; Recorded version updated: 2023-11-06T07:39:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.14495", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2310.14495"}} @misc{arxiv_2310_14495, title = {{InstructExcel: A Benchmark for Natural Language Instruction in Excel}}, author = {{Justin Payan} and {Swaroop Mishra} and {Mukul Singh} and {Carina Negreanu} and {Christian Poelitz} and {Chitta Baral} and {Subhro Roy} and {Rasika Chakravarthy} and {Benjamin Van Durme} and {Elnaz Nouri}}, year = {2023}, eprint = {2310.14495v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.14495v1}, note = {First published: 2023-10-23; Recorded arXiv version: v1; Recorded version updated: 2023-10-23T02:00:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.16042", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2310.16042"}} @misc{arxiv_2310_16042, title = {{WebWISE: Web Interface Control and Sequential Exploration with Large Language Models}}, author = {{Heyi Tao} and {Sethuraman T} and {Michal Shlapentokh-Rothman} and {Derek Hoiem}}, year = {2023}, eprint = {2310.16042v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.16042v2}, note = {First published: 2023-10-24; Recorded arXiv version: v2; Recorded version updated: 2023-10-25T03:54:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2310.18331", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2310.18331"}} @misc{arxiv_2310_18331, title = {{AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models}}, author = {{Jiarun Liu} and {Wentao Hu} and {Chunhong Zhang}}, year = {2023}, eprint = {2310.18331v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.18331v2}, note = {First published: 2023-10-20; Recorded arXiv version: v2; Recorded version updated: 2023-10-31T06:25:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2311.01767", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2311.01767"}} @misc{arxiv_2311_01767, title = {{PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion}}, author = {{Yiduo Guo} and {Zekai Zhang} and {Yaobo Liang} and {Dongyan Zhao} and {Nan Duan}}, year = {2023}, eprint = {2311.01767v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.01767v2}, note = {First published: 2023-11-03; Recorded arXiv version: v2; Recorded version updated: 2023-11-07T10:13:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2311.07562", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2311.07562"}} @misc{arxiv_2311_07562, title = {{GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation}}, author = {{An Yan} and {Zhengyuan Yang} and {Wanrong Zhu} and {Kevin Lin} and {Linjie Li} and {Jianfeng Wang} and {Jianwei Yang} and {Yiwu Zhong} and {Julian McAuley} and {Jianfeng Gao} and {Zicheng Liu} and {Lijuan Wang}}, year = {2023}, eprint = {2311.07562v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.07562v1}, note = {First published: 2023-11-13; Recorded arXiv version: v1; Recorded version updated: 2023-11-13T18:53:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2311.12983", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2311.12983"}} @misc{arxiv_2311_12983, title = {{GAIA: a benchmark for General AI Assistants}}, author = {{Grégoire Mialon} and {Clémentine Fourrier} and {Craig Swift} and {Thomas Wolf} and {Yann LeCun} and {Thomas Scialom}}, year = {2023}, eprint = {2311.12983v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.12983v1}, note = {First published: 2023-11-21; Recorded arXiv version: v1; Recorded version updated: 2023-11-21T20:34:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2311.18751", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2311.18751"}} @misc{arxiv_2311_18751, title = {{Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web}}, author = {{Hiroki Furuta} and {Yutaka Matsuo} and {Aleksandra Faust} and {Izzeddin Gur}}, year = {2023}, eprint = {2311.18751v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.18751v3}, note = {First published: 2023-11-30; Recorded arXiv version: v3; Recorded version updated: 2024-12-31T04:24:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.03003", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.03003"}} @misc{arxiv_2312_03003, title = {{Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation}}, author = {{Sunjae Lee} and {Junyoung Choi} and {Jungjae Lee} and {Munim Hasan Wasi} and {Hojun Choi} and {Steven Y. Ko} and {Sangeun Oh} and {Insik Shin}}, year = {2023}, eprint = {2312.03003v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.03003v3}, note = {First published: 2023-12-04; Recorded arXiv version: v3; Recorded version updated: 2024-10-16T08:15:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.06677", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.06677"}} @misc{arxiv_2312_06677, title = {{Intelligent Virtual Assistants with LLM-based Process Automation}}, author = {{Yanchu Guan} and {Dong Wang} and {Zhixuan Chu} and {Shiyu Wang} and {Feiyue Ni} and {Ruihua Song} and {Longfei Li} and {Jinjie Gu} and {Chenyi Zhuang}}, year = {2023}, eprint = {2312.06677v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.06677v1}, note = {First published: 2023-12-04; Recorded arXiv version: v1; Recorded version updated: 2023-12-04T07:51:58Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2312.08914", "catalog_id": "arxiv:2312.08914", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2312.08914"}, "publication": {"authors": ["Wenyi Hong", "Weihan Wang", "Qingsong Lv", "Jiazheng Xu", "Wenmeng Yu", "Junhui Ji", "Yan Wang", "Zihan Wang", "Yuxiao Dong", "Ming Ding", "Jie Tang"], "date_basis": "Year from publisher citation metadata and month from the same page's embedded BibTeX; no day is supplied.", "date_parts": [2024, 6], "doi": null, "event_dates": null, "evidence_urls": ["https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html", "https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher page directly links this arXiv identifier. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, and landing page list eleven authors; the retained arXiv snapshot lists fourteen. Each edition retains its own authors.", "pages": "14281-14290", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf", "publisher": null, "series": null, "title": "CogAgent: A Visual Language Model for GUI Agents", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition", "volume": null}} @misc{arxiv_2312_08914, title = {{CogAgent: A Visual Language Model for GUI Agents}}, author = {{Wenyi Hong} and {Weihan Wang} and {Qingsong Lv} and {Jiazheng Xu} and {Wenmeng Yu} and {Junhui Ji} and {Yan Wang} and {Zihan Wang} and {Yuxuan Zhang} and {Juanzi Li} and {Bin Xu} and {Yuxiao Dong} and {Ming Ding} and {Jie Tang}}, year = {2023}, eprint = {2312.08914v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.08914v3}, note = {First published: 2023-12-14; Recorded arXiv version: v3; Recorded version updated: 2024-12-27T06:56:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.11190", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.11190"}} @misc{arxiv_2312_11190, title = {{VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning}}, author = {{Yunpeng Song} and {Yiheng Bian} and {Yongtao Tang} and {Guiyu Ma} and {Zhongmin Cai}}, year = {2023}, eprint = {2312.11190v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.11190v2}, note = {First published: 2023-12-18; Recorded arXiv version: v2; Recorded version updated: 2024-07-29T14:52:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.13108", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.13108"}} @misc{arxiv_2312_13108, title = {{ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation}}, author = {{Difei Gao} and {Lei Ji} and {Zechen Bai} and {Mingyu Ouyang} and {Peiran Li} and {Dongxing Mao} and {Qinchen Wu} and {Weichen Zhang} and {Peiyi Wang} and {Xiangwu Guo} and {Hengxu Wang} and {Luowei Zhou} and {Mike Zheng Shou}}, year = {2023}, eprint = {2312.13108v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.13108v2}, note = {First published: 2023-12-20; Recorded arXiv version: v2; Recorded version updated: 2024-01-01T14:26:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.13771", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.13771"}} @misc{arxiv_2312_13771, title = {{AppAgent: Multimodal Agents as Smartphone Users}}, author = {{Chi Zhang} and {Zhao Yang} and {Jiaxuan Liu} and {Yanda Li} and {Yucheng Han} and {Xin Chen} and {Zebiao Huang} and {Bin Fu} and {Gang Yu}}, year = {2023}, eprint = {2312.13771v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.13771v3}, note = {First published: 2023-12-21; Recorded arXiv version: v3; Recorded version updated: 2026-07-05T07:51:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.15820", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.15820"}} @misc{arxiv_2312_15820, title = {{WebVLN: Vision-and-Language Navigation on Websites}}, author = {{Qi Chen} and {Dileepa Pitawela} and {Chongyang Zhao} and {Gengze Zhou} and {Hsiang-Ting Chen} and {Qi Wu}}, year = {2023}, eprint = {2312.15820v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.15820v1}, note = {First published: 2023-12-25; Recorded arXiv version: v1; Recorded version updated: 2023-12-25T22:13:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2312.16062", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2312.16062"}} @misc{arxiv_2312_16062, title = {{AutoTask: Executing Arbitrary Voice Commands by Exploring and Learning from Mobile GUI}}, author = {{Lihang Pan} and {Bowen Wang} and {Chun Yu} and {Yuxuan Chen} and {Xiangyu Zhang} and {Yuanchun Shi}}, year = {2023}, eprint = {2312.16062v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.16062v1}, note = {First published: 2023-12-26; Recorded arXiv version: v1; Recorded version updated: 2023-12-26T14:20:36Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2401.01614", "catalog_id": "arxiv:2401.01614", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2401.01614"}, "publication": {"authors": ["Boyuan Zheng", "Boyu Gou", "Jihyung Kil", "Huan Sun", "Yu Su"], "date_basis": "Explicit publisher metadata: 2024/07/08; precision=day.", "date_parts": [2024, 7, 8], "doi": null, "event_dates": "21--27 Jul 2024", "evidence_urls": ["https://proceedings.mlr.press/v235/zheng24e.html"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "61349-61385", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v235/main/assets/zheng24e/zheng24e.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "GPT-4V(ision) is a Generalist Web Agent, if Grounded", "type": "conference-paper", "url": "https://proceedings.mlr.press/v235/zheng24e.html", "venue": "Proceedings of the 41st International Conference on Machine Learning", "volume": "235"}} @misc{arxiv_2401_01614, title = {{GPT-4V(ision) is a Generalist Web Agent, if Grounded}}, author = {{Boyuan Zheng} and {Boyu Gou} and {Jihyung Kil} and {Huan Sun} and {Yu Su}}, year = {2024}, eprint = {2401.01614v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.01614v2}, note = {First published: 2024-01-03; Recorded arXiv version: v2; Recorded version updated: 2024-03-12T23:14:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2401.04124", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2401.04124"}} @misc{arxiv_2401_04124, title = {{MobileAgent: enhancing mobile control via human-machine interaction and SOP integration}}, author = {{Tinghe Ding}}, year = {2024}, eprint = {2401.04124v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.04124v3}, note = {First published: 2024-01-04; Recorded arXiv version: v3; Recorded version updated: 2024-01-17T06:35:45Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2401.10935", "catalog_id": "arxiv:2401.10935", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2401.10935"}, "publication": {"authors": ["Kanzhi Cheng", "Qiushi Sun", "Yougang Chu", "Fangzhi Xu", "Yantao Li", "Jianbing Zhang", "Zhiyong Wu"], "date_basis": "Explicit publisher metadata: 2024/8; precision=month.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.acl-long.505", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.acl-long.505/", "https://aclanthology.org/2024.acl-long.505.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The ACL landing metadata spells the fifth author Li YanTao. The formal PDF title page spells Yantao Li; the publication author field uses the PDF. The retained arXiv author list is untouched. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "9313-9332", "pdf_url": "https://aclanthology.org/2024.acl-long.505.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.505/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2401_10935, title = {{SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents}}, author = {{Kanzhi Cheng} and {Qiushi Sun} and {Yougang Chu} and {Fangzhi Xu} and {Yantao Li} and {Jianbing Zhang} and {Zhiyong Wu}}, year = {2024}, eprint = {2401.10935v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.10935v2}, note = {First published: 2024-01-17; Recorded arXiv version: v2; Recorded version updated: 2024-02-23T04:36:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2401.13178", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2401.13178"}} @misc{arxiv_2401_13178, title = {{AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents}}, author = {{Chang Ma} and {Junlei Zhang} and {Zhihao Zhu} and {Cheng Yang} and {Yujiu Yang} and {Yaohui Jin} and {Zhenzhong Lan} and {Lingpeng Kong} and {Junxian He}}, year = {2024}, eprint = {2401.13178v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.13178v2}, note = {First published: 2024-01-24; Recorded arXiv version: v2; Recorded version updated: 2024-12-23T20:12:48Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2401.13649", "catalog_id": "arxiv:2401.13649", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2401.13649"}, "publication": {"authors": ["Jing Yu Koh", "Robert Lo", "Lawrence Jang", "Vikram Duvvur", "Ming Chong Lim", "Po-Yu Huang", "Graham Neubig", "Shuyan Zhou", "Ruslan Salakhutdinov", "Daniel Fried"], "date_basis": "Explicit publisher metadata: 2024/8; precision=month.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.acl-long.50", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.acl-long.50/", "https://aclanthology.org/2024.acl-long.50.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The formal PDF title adds Visually Grounded; the landing metadata uses Visual Web Tasks. PDF authors include Ming Chong Lim and Ruslan Salakhutdinov; the landing abbreviates them to Ming Lim and Russ Salakhutdinov. Publication title/authors use the PDF; the retained arXiv title remains unchanged. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "881-905", "pdf_url": "https://aclanthology.org/2024.acl-long.50.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "VisualWebArena: Evaluating Multimodal Agents on Realistic Visually Grounded Web Tasks", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.50/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2401_13649, title = {{VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks}}, author = {{Jing Yu Koh} and {Robert Lo} and {Lawrence Jang} and {Vikram Duvvur} and {Ming Chong Lim} and {Po-Yu Huang} and {Graham Neubig} and {Shuyan Zhou} and {Ruslan Salakhutdinov} and {Daniel Fried}}, year = {2024}, eprint = {2401.13649v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.13649v2}, note = {First published: 2024-01-24; Recorded arXiv version: v2; Recorded version updated: 2024-06-06T02:01:09Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2401.13919", "catalog_id": "arxiv:2401.13919", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2401.13919"}, "publication": {"authors": ["Hongliang He", "Wenlin Yao", "Kaixin Ma", "Wenhao Yu", "Yong Dai", "Hongming Zhang", "Zhenzhong Lan", "Dong Yu"], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.acl-long.371", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.acl-long.371/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "6864-6890", "pdf_url": "https://aclanthology.org/2024.acl-long.371.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.371/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2401_13919, title = {{WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models}}, author = {{Hongliang He} and {Wenlin Yao} and {Kaixin Ma} and {Wenhao Yu} and {Yong Dai} and {Hongming Zhang} and {Zhenzhong Lan} and {Dong Yu}}, year = {2024}, eprint = {2401.13919v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.13919v4}, note = {First published: 2024-01-25; Recorded arXiv version: v4; Recorded version updated: 2024-06-06T18:37:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2401.14268", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2401.14268"}} @misc{arxiv_2401_14268, title = {{GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning}}, author = {{Minh Duc Vu} and {Han Wang} and {Zhuang Li} and {Jieshan Chen} and {Shengdong Zhao} and {Zhenchang Xing} and {Chunyang Chen}}, year = {2024}, eprint = {2401.14268v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.14268v3}, note = {First published: 2024-01-25; Recorded arXiv version: v3; Recorded version updated: 2024-08-14T00:48:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2401.16158", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2401.16158"}} @misc{arxiv_2401_16158, title = {{Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception}}, author = {{Junyang Wang} and {Haiyang Xu} and {Jiabo Ye} and {Ming Yan} and {Weizhou Shen} and {Ji Zhang} and {Fei Huang} and {Jitao Sang}}, year = {2024}, eprint = {2401.16158v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.16158v2}, note = {First published: 2024-01-29; Recorded arXiv version: v2; Recorded version updated: 2024-04-18T06:53:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.04476", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.04476"}} @misc{arxiv_2402_04476, title = {{Dual-View Visual Contextualization for Web Navigation}}, author = {{Jihyung Kil} and {Chan Hee Song} and {Boyuan Zheng} and {Xiang Deng} and {Yu Su} and {Wei-Lun Chao}}, year = {2024}, eprint = {2402.04476v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.04476v2}, note = {First published: 2024-02-06; Recorded arXiv version: v2; Recorded version updated: 2024-03-30T05:18:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.04615", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.04615"}} @misc{arxiv_2402_04615, title = {{ScreenAI: A Vision-Language Model for UI and Infographics Understanding}}, author = {{Gilles Baechler} and {Srinivas Sunkara} and {Maria Wang} and {Fedir Zubach} and {Hassan Mansoor} and {Vincent Etter} and {Victor Cărbune} and {Jason Lin} and {Jindong Chen} and {Abhanshu Sharma}}, year = {2024}, eprint = {2402.04615v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.04615v3}, note = {First published: 2024-02-07; Recorded arXiv version: v3; Recorded version updated: 2024-07-04T07:08:15Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2402.05930", "catalog_id": "arxiv:2402.05930", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2402.05930"}, "publication": {"authors": ["Xing Han L\u00f9", "Zden\u011bk Kasner", "Siva Reddy"], "date_basis": "Explicit publisher metadata: 2024/07/08; precision=day.", "date_parts": [2024, 7, 8], "doi": null, "event_dates": "21--27 Jul 2024", "evidence_urls": ["https://proceedings.mlr.press/v235/lu24e.html", "https://raw.githubusercontent.com/mlresearch/v235/main/assets/lu24e/lu24e.pdf"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The PMLR landing renders Xing Han Lu; the paper title page has Xing Han L\u00f9. Publication authors use the PDF. The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "33007-33056", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v235/main/assets/lu24e/lu24e.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "WebLINX: Real-World Website Navigation with Multi-Turn Dialogue", "type": "conference-paper", "url": "https://proceedings.mlr.press/v235/lu24e.html", "venue": "Proceedings of the 41st International Conference on Machine Learning", "volume": "235"}} @misc{arxiv_2402_05930, title = {{WebLINX: Real-World Website Navigation with Multi-Turn Dialogue}}, author = {{Xing Han Lù} and {Zdeněk Kasner} and {Siva Reddy}}, year = {2024}, eprint = {2402.05930v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.05930v2}, note = {First published: 2024-02-08; Recorded arXiv version: v2; Recorded version updated: 2024-09-10T22:22:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.06596", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.06596"}} @misc{arxiv_2402_06596, title = {{Understanding the Weakness of Large Language Model Agents within a Complex Android Environment}}, author = {{Mingzhe Xing} and {Rongkai Zhang} and {Hui Xue} and {Qi Chen} and {Fan Yang} and {Zhen Xiao}}, year = {2024}, eprint = {2402.06596v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.06596v1}, note = {First published: 2024-02-09; Recorded arXiv version: v1; Recorded version updated: 2024-02-09T18:19:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.07456", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.07456"}} @misc{arxiv_2402_07456, title = {{OS-Copilot: Towards Generalist Computer Agents with Self-Improvement}}, author = {{Zhiyong Wu} and {Chengcheng Han} and {Zichen Ding} and {Zhenmin Weng} and {Zhoumianze Liu} and {Shunyu Yao} and {Tao Yu} and {Lingpeng Kong}}, year = {2024}, eprint = {2402.07456v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.07456v2}, note = {First published: 2024-02-12; Recorded arXiv version: v2; Recorded version updated: 2024-02-15T09:30:48Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2402.07939", "catalog_id": "arxiv:2402.07939", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2402.07939"}, "publication": {"authors": ["Chaoyun Zhang", "Liqun Li", "Shilin He", "Xu Zhang", "Bo Qiao", "Si Qin", "Minghua Ma", "Yu Kang", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-long.26", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-long.26/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "597-622", "pdf_url": "https://aclanthology.org/2025.naacl-long.26.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "UFO: A UI-Focused Agent for Windows OS Interaction", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.26/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2402_07939, title = {{UFO: A UI-Focused Agent for Windows OS Interaction}}, author = {{Chaoyun Zhang} and {Liqun Li} and {Shilin He} and {Xu Zhang} and {Bo Qiao} and {Si Qin} and {Minghua Ma} and {Yu Kang} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang} and {Qi Zhang}}, year = {2024}, eprint = {2402.07939v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.07939v5}, note = {First published: 2024-02-08; Recorded arXiv version: v5; Recorded version updated: 2024-05-23T05:18:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.07945", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.07945"}} @misc{arxiv_2402_07945, title = {{ScreenAgent: A Vision Language Model-driven Computer Control Agent}}, author = {{Runliang Niu} and {Jindong Li} and {Shiqi Wang} and {Yali Fu} and {Xiyu Hu} and {Xueyuan Leng} and {He Kong} and {Yi Chang} and {Qi Wang}}, year = {2024}, eprint = {2402.07945v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.07945v1}, note = {First published: 2024-02-09; Recorded arXiv version: v1; Recorded version updated: 2024-02-09T02:33:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.10196", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2402.10196"}} @misc{arxiv_2402_10196, title = {{A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents}}, author = {{Lingbo Mo} and {Zeyi Liao} and {Boyuan Zheng} and {Yu Su} and {Chaowei Xiao} and {Huan Sun}}, year = {2024}, eprint = {2402.10196v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.10196v1}, note = {First published: 2024-02-15; Recorded arXiv version: v1; Recorded version updated: 2024-02-15T18:51:32Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2402.11941", "catalog_id": "arxiv:2402.11941", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2402.11941"}, "publication": {"authors": ["Xinbei Ma", "Zhuosheng Zhang", "Hai Zhao (\u8d75\u6d77)"], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.findings-acl.539", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-acl.539"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "9097-9110", "pdf_url": "https://aclanthology.org/2024.findings-acl.539.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-acl.539", "venue": "Findings of the Association for Computational Linguistics: ACL 2024", "volume": null}} @misc{arxiv_2402_11941, title = {{CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation}}, author = {{Xinbei Ma} and {Zhuosheng Zhang} and {Hai Zhao}}, year = {2024}, eprint = {2402.11941v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.11941v3}, note = {First published: 2024-02-19; Recorded arXiv version: v3; Recorded version updated: 2024-06-02T13:25:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.14073", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2402.14073"}} @misc{arxiv_2402_14073, title = {{Improving Language Understanding from Screenshots}}, author = {{Tianyu Gao} and {Zirui Wang} and {Adithya Bhaskar} and {Danqi Chen}}, year = {2024}, eprint = {2402.14073v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.14073v1}, note = {First published: 2024-02-21; Recorded arXiv version: v1; Recorded version updated: 2024-02-21T19:01:03Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2402.15057", "catalog_id": "arxiv:2402.15057", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2402.15057"}, "publication": {"authors": ["Yang Deng", "Xuan Zhang", "Wenxuan Zhang", "Yifei Yuan", "See Kiong Ng", "Tat-Seng Chua"], "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 8], "doi": "10.18653/v1/2024.acl-long.477", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.acl-long.477/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "8795-8812", "pdf_url": "https://aclanthology.org/2024.acl-long.477.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "On the Multi-turn Instruction Following for Conversational Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.acl-long.477/", "venue": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2402_15057, title = {{On the Multi-turn Instruction Following for Conversational Web Agents}}, author = {{Yang Deng} and {Xuan Zhang} and {Wenxuan Zhang} and {Yifei Yuan} and {See-Kiong Ng} and {Tat-Seng Chua}}, year = {2024}, eprint = {2402.15057v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.15057v1}, note = {First published: 2024-02-23; Recorded arXiv version: v1; Recorded version updated: 2024-02-23T02:18:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.16965", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.16965"}} @misc{arxiv_2402_16965, title = {{WIPI: A New Web Threat for LLM-Driven Web Agents}}, author = {{Fangzhou Wu} and {Shutong Wu} and {Yulong Cao} and {Chaowei Xiao}}, year = {2024}, eprint = {2402.16965v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.16965v1}, note = {First published: 2024-02-26; Recorded arXiv version: v1; Recorded version updated: 2024-02-26T19:01:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2402.17553", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.17553"}} @misc{arxiv_2402_17553, title = {{OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web}}, author = {{Raghav Kapoor} and {Yash Parag Butala} and {Melisa Russak} and {Jing Yu Koh} and {Kiran Kamble} and {Waseem Alshikh} and {Ruslan Salakhutdinov}}, year = {2024}, eprint = {2402.17553v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.17553v3}, note = {First published: 2024-02-27; Recorded arXiv version: v3; Recorded version updated: 2024-07-21T23:16:13Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2403.02713", "catalog_id": "arxiv:2403.02713", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2403.02713"}, "publication": {"authors": ["Jiwen Zhang (\u5f20\u9701\u96ef)", "Jihao Wu", "Teng Yihua", "Minghui Liao", "Nuo Xu", "Xiao Xiao", "Zhongyu Wei (\u9b4f\u5fe0\u94b0)", "Duyu Tang"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.findings-emnlp.702", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-emnlp.702/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "12016-12031", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.702.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Android in the Zoo: Chain-of-Action-Thought for GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.702/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null}} @misc{arxiv_2403_02713, title = {{Android in the Zoo: Chain-of-Action-Thought for GUI Agents}}, author = {{Jiwen Zhang} and {Jihao Wu} and {Yihua Teng} and {Minghui Liao} and {Nuo Xu} and {Xiao Xiao} and {Zhongyu Wei} and {Duyu Tang}}, year = {2024}, eprint = {2403.02713v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.02713v2}, note = {First published: 2024-03-05; Recorded arXiv version: v2; Recorded version updated: 2024-07-13T02:12:30Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2403.03186", "catalog_id": "arxiv:2403.03186", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2403.03186"}, "publication": {"authors": ["Weihao Tan", "Wentao Zhang", "Xinrun Xu", "Haochong Xia", "Ziluo Ding", "Boyu Li", "Bohan Zhou", "Junpeng Yue", "Jiechuan Jiang", "Yewen Li", "Ruyi An", "Molei Qin", "Chuqiao Zong", "Longtao Zheng", "Yujie Wu", "Xiaoqiang Chai", "Yifei Bi", "Tianbao Xie", "Pengjie Gu", "Xiyun Li", "Ceyao Zhang", "Long Tian", "Chaojie Wang", "Xinrun Wang", "B\u00f6rje F. Karlsson", "Bo An", "Shuicheng Yan", "Zongqing Lu"], "date_basis": "Explicit publisher metadata: 2025/10/06; precision=day.", "date_parts": [2025, 10, 6], "doi": null, "event_dates": "13--19 Jul 2025", "evidence_urls": ["https://proceedings.mlr.press/v267/tan25h.html"], "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.", "issue": null, "notes": "The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.", "pages": "58658-58725", "pdf_url": "https://raw.githubusercontent.com/mlresearch/v267/main/assets/tan25h/tan25h.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "Cradle: Empowering Foundation Agents towards General Computer Control", "type": "conference-paper", "url": "https://proceedings.mlr.press/v267/tan25h.html", "venue": "Proceedings of the 42nd International Conference on Machine Learning", "volume": "267"}} @misc{arxiv_2403_03186, title = {{Cradle: Empowering Foundation Agents Towards General Computer Control}}, author = {{Weihao Tan} and {Wentao Zhang} and {Xinrun Xu} and {Haochong Xia} and {Ziluo Ding} and {Boyu Li} and {Bohan Zhou} and {Junpeng Yue} and {Jiechuan Jiang} and {Yewen Li} and {Ruyi An} and {Molei Qin} and {Chuqiao Zong} and {Longtao Zheng} and {Yujie Wu} and {Xiaoqiang Chai} and {Yifei Bi} and {Tianbao Xie} and {Pengjie Gu} and {Xiyun Li} and {Ceyao Zhang} and {Long Tian} and {Chaojie Wang} and {Xinrun Wang} and {Börje F. Karlsson} and {Bo An} and {Shuicheng Yan} and {Zongqing Lu}}, year = {2024}, eprint = {2403.03186v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.03186v3}, note = {First published: 2024-03-05; Recorded arXiv version: v3; Recorded version updated: 2024-07-02T17:23:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2403.03788", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2403.03788"}} @misc{arxiv_2403_03788, title = {{PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion}}, author = {{Zekai Zhang} and {Yiduo Guo} and {Yaobo Liang} and {Dongyan Zhao} and {Nan Duan}}, year = {2024}, eprint = {2403.03788v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.03788v1}, note = {First published: 2024-03-06; Recorded arXiv version: v1; Recorded version updated: 2024-03-06T15:33:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2403.04984", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2403.04984"}} @misc{arxiv_2403_04984, title = {{UI Semantic Group Detection: Grouping UI Elements with Similar Semantics in Mobile Graphical User Interface}}, author = {{Shuhong Xiao} and {Yunnong Chen} and {Yaxuan Song} and {Liuqing Chen} and {Lingyun Sun} and {Yankun Zhen} and {Yanfang Chang}}, year = {2024}, eprint = {2403.04984v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.04984v1}, note = {First published: 2024-03-08; Recorded arXiv version: v1; Recorded version updated: 2024-03-08T01:52:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2403.07718", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2403.07718"}} @misc{arxiv_2403_07718, title = {{WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?}}, author = {{Alexandre Drouin} and {Maxime Gasse} and {Massimo Caccia} and {Issam H. Laradji} and {Manuel Del Verme} and {Tom Marty} and {Léo Boisvert} and {Megh Thakkar} and {Quentin Cappart} and {David Vazquez} and {Nicolas Chapados} and {Alexandre Lacoste}}, year = {2024}, eprint = {2403.07718v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.07718v5}, note = {First published: 2024-03-12; Recorded arXiv version: v5; Recorded version updated: 2024-07-23T06:19:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2403.10170", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2403.10170"}} @misc{arxiv_2403_10170, title = {{Computer User Interface Understanding. A New Dataset and a Learning Framework}}, author = {{Andrés Muñoz} and {Daniel Borrajo}}, year = {2024}, eprint = {2403.10170v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.10170v2}, note = {First published: 2024-03-15; Recorded arXiv version: v2; Recorded version updated: 2024-08-27T18:36:12Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2403.11905", "catalog_id": "arxiv:2403.11905", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2403.11905"}, "publication": {"authors": ["Kevin Xu", "Yeganeh Kordi", "Tanay Nayak", "Adi Asija", "Yizhong Wang", "Kate Sanders", "Adam Byerly", "Jingyu Zhang", "Benjamin Van Durme", "Daniel Khashabi"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-long.188", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-long.188/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "3694-3710", "pdf_url": "https://aclanthology.org/2025.naacl-long.188.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "TurkingBench: A Challenge Benchmark for Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.188/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2403_11905, title = {{Tur[k]ingBench: A Challenge Benchmark for Web Agents}}, author = {{Kevin Xu} and {Yeganeh Kordi} and {Tanay Nayak} and {Adi Asija} and {Yizhong Wang} and {Kate Sanders} and {Adam Byerly} and {Jingyu Zhang} and {Benjamin Van Durme} and {Daniel Khashabi}}, year = {2024}, eprint = {2403.11905v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.11905v4}, note = {First published: 2024-03-18; Recorded arXiv version: v4; Recorded version updated: 2025-02-22T01:33:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2403.17918", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2403.17918"}} @misc{arxiv_2403_17918, title = {{AgentStudio: A Toolkit for Building General Virtual Agents}}, author = {{Longtao Zheng} and {Zhiyuan Huang} and {Zhenghai Xue} and {Xinrun Wang} and {Bo An} and {Shuicheng Yan}}, year = {2024}, eprint = {2403.17918v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.17918v3}, note = {First published: 2024-03-26; Recorded arXiv version: v3; Recorded version updated: 2025-02-14T08:13:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2403.20329", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2403.20329"}} @misc{arxiv_2403_20329, title = {{ReALM: Reference Resolution As Language Modeling}}, author = {{Joel Ruben Antony Moniz} and {Soundarya Krishnan} and {Melis Ozyildirim} and {Prathamesh Saraf} and {Halim Cagri Ates} and {Yuan Zhang} and {Hong Yu}}, year = {2024}, eprint = {2403.20329v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.20329v2}, note = {First published: 2024-03-29; Recorded arXiv version: v2; Recorded version updated: 2024-08-19T03:06:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.02475", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.02475"}} @misc{arxiv_2404_02475, title = {{Prompt2Task: Automating UI Tasks on Smartphones from Textual Prompts}}, author = {{Tian Huang} and {Chun Yu} and {Weinan Shi} and {Zijian Peng} and {David Yang} and {Weiqi Sun} and {Yuanchun Shi}}, year = {2024}, eprint = {2404.02475v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.02475v2}, note = {First published: 2024-04-03; Recorded arXiv version: v2; Recorded version updated: 2025-03-18T09:59:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.03648", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.03648"}} @misc{arxiv_2404_03648, title = {{AutoWebGLM: A Large Language Model-based Web Navigating Agent}}, author = {{Hanyu Lai} and {Xiao Liu} and {Iat Long Iong} and {Shuntian Yao} and {Yuxuan Chen} and {Pengbo Shen} and {Hao Yu} and {Hanchen Zhang} and {Xiaohan Zhang} and {Yuxiao Dong} and {Jie Tang}}, year = {2024}, eprint = {2404.03648v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.03648v2}, note = {First published: 2024-04-04; Recorded arXiv version: v2; Recorded version updated: 2024-10-12T05:05:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.05719", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.05719"}} @misc{arxiv_2404_05719, title = {{Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs}}, author = {{Keen You} and {Haotian Zhang} and {Eldon Schoop} and {Floris Weers} and {Amanda Swearngin} and {Jeffrey Nichols} and {Yinfei Yang} and {Zhe Gan}}, year = {2024}, eprint = {2404.05719v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.05719v1}, note = {First published: 2024-04-08; Recorded arXiv version: v1; Recorded version updated: 2024-04-08T17:55:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.05902", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.05902"}} @misc{arxiv_2404_05902, title = {{WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents}}, author = {{Michael Lutz} and {Arth Bohra} and {Manvel Saroyan} and {Artem Harutyunyan} and {Giovanni Campagna}}, year = {2024}, eprint = {2404.05902v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.05902v1}, note = {First published: 2024-04-08; Recorded arXiv version: v1; Recorded version updated: 2024-04-08T23:10:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.05955", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.05955"}} @misc{arxiv_2404_05955, title = {{VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?}}, author = {{Junpeng Liu} and {Yifan Song} and {Bill Yuchen Lin} and {Wai Lam} and {Graham Neubig} and {Yuanzhi Li} and {Xiang Yue}}, year = {2024}, eprint = {2404.05955v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.05955v1}, note = {First published: 2024-04-09; Recorded arXiv version: v1; Recorded version updated: 2024-04-09T02:29:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.06474", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.06474"}} @misc{arxiv_2404_06474, title = {{Autonomous Evaluation and Refinement of Digital Agents}}, author = {{Jiayi Pan} and {Yichi Zhang} and {Nicholas Tomlin} and {Yifei Zhou} and {Sergey Levine} and {Alane Suhr}}, year = {2024}, eprint = {2404.06474v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.06474v3}, note = {First published: 2024-04-09; Recorded arXiv version: v3; Recorded version updated: 2024-10-07T14:19:37Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2404.07972", "catalog_id": "arxiv:2404.07972", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2404.07972"}, "publication": {"authors": ["Tianbao Xie", "Danyang Zhang", "Jixuan Chen", "Xiaochuan Li", "Siheng Zhao", "Ruisheng Cao", "Toh J. Hua", "Zhoujun Cheng", "Dongchan Shin", "Fangyu Lei", "Yitao Liu", "Yiheng Xu", "Shuyan Zhou", "Silvio Savarese", "Caiming Xiong", "Victor Zhong", "Tao Yu"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-1650", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "52040-52094", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/5d413e48f84dc61244b6be550f1cd8f5-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2404_07972, title = {{OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments}}, author = {{Tianbao Xie} and {Danyang Zhang} and {Jixuan Chen} and {Xiaochuan Li} and {Siheng Zhao} and {Ruisheng Cao} and {Toh Jing Hua} and {Zhoujun Cheng} and {Dongchan Shin} and {Fangyu Lei} and {Yitao Liu} and {Yiheng Xu} and {Shuyan Zhou} and {Silvio Savarese} and {Caiming Xiong} and {Victor Zhong} and {Tao Yu}}, year = {2024}, eprint = {2404.07972v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.07972v2}, note = {First published: 2024-04-11; Recorded arXiv version: v2; Recorded version updated: 2024-05-30T08:55:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.08755", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.08755"}} @misc{arxiv_2404_08755, title = {{Training a Vision Language Model as Smartphone Assistant}}, author = {{Nicolai Dorka} and {Janusz Marecki} and {Ammar Anwar}}, year = {2024}, eprint = {2404.08755v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.08755v1}, note = {First published: 2024-04-12; Recorded arXiv version: v1; Recorded version updated: 2024-04-12T18:28:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.08860", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.08860"}} @misc{arxiv_2404_08860, title = {{Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking}}, author = {{Lei Ding} and {Jeshwanth Bheemanpally} and {Yi Zhang}}, year = {2024}, eprint = {2404.08860v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.08860v3}, note = {First published: 2024-04-13; Recorded arXiv version: v3; Recorded version updated: 2024-07-09T01:14:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.08948", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.08948"}} @misc{arxiv_2404_08948, title = {{Large Language Models for Mobile GUI Text Input Generation: An Empirical Study}}, author = {{Chenhui Cui} and {Tao Li} and {Junjie Wang} and {Chunyang Chen} and {Dave Towey} and {Rubing Huang}}, year = {2024}, eprint = {2404.08948v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.08948v4}, note = {First published: 2024-04-13; Recorded arXiv version: v4; Recorded version updated: 2026-06-25T14:05:55Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2404.09992", "catalog_id": "arxiv:2404.09992", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2404.09992"}, "publication": {"authors": ["Shulin Tian", "Ziniu Zhang", "Liang-Yu Chen", "Ziwei Liu"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.703", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.703/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "13682-13697", "pdf_url": "https://aclanthology.org/2025.findings-acl.703.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MMInA: Benchmarking Multihop Multimodal Internet Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.703/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2404_09992, title = {{MMInA: Benchmarking Multihop Multimodal Internet Agents}}, author = {{Shulin Tian} and {Ziniu Zhang} and {Liangyu Chen} and {Ziwei Liu}}, year = {2024}, eprint = {2404.09992v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.09992v2}, note = {First published: 2024-04-15; Recorded arXiv version: v2; Recorded version updated: 2025-06-29T05:24:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.10887", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.10887"}} @misc{arxiv_2404_10887, title = {{Grounded Language Agent for Product Search via Intelligent Web Interactions}}, author = {{Moghis Fereidouni} and {Adib Mosharrof} and {A. B. Siddique}}, year = {2024}, eprint = {2404.10887v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.10887v2}, note = {First published: 2024-04-16; Recorded arXiv version: v2; Recorded version updated: 2025-01-26T19:07:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.16048", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.16048"}} @misc{arxiv_2404_16048, title = {{GUIDE: Graphical User Interface Data for Execution}}, author = {{Rajat Chawla} and {Adarsh Jha} and {Muskaan Kumar} and {Mukunda NS} and {Ishaan Bhola}}, year = {2024}, eprint = {2404.16048v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.16048v2}, note = {First published: 2024-04-09; Recorded arXiv version: v2; Recorded version updated: 2024-10-27T05:54:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.16054", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.16054"}} @misc{arxiv_2404_16054, title = {{LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation}}, author = {{Li Zhang} and {Shihe Wang} and {Xianqing Jia} and {Zhihan Zheng} and {Yunhe Yan} and {Longxi Gao} and {Yuanchun Li} and {Mengwei Xu}}, year = {2024}, eprint = {2404.16054v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.16054v2}, note = {First published: 2024-04-12; Recorded arXiv version: v2; Recorded version updated: 2024-08-02T13:49:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.16660", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.16660"}} @misc{arxiv_2404_16660, title = {{Benchmarking Mobile Device Control Agents across Diverse Configurations}}, author = {{Juyong Lee} and {Taywon Min} and {Minyong An} and {Dongyoon Hahm} and {Haeone Lee} and {Changyeon Kim} and {Kimin Lee}}, year = {2024}, eprint = {2404.16660v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.16660v3}, note = {First published: 2024-04-25; Recorded arXiv version: v3; Recorded version updated: 2025-07-21T02:55:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2404.18074", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.18074"}} @misc{arxiv_2404_18074, title = {{MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot}}, author = {{Zirui Song} and {Yaohang Li} and {Meng Fang} and {Yanda Li} and {Zhenhao Chen} and {Zecheng Shi} and {Yuan Huang} and {Xiuying Chen} and {Ling Chen}}, year = {2024}, eprint = {2404.18074v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.18074v3}, note = {First published: 2024-04-28; Recorded arXiv version: v3; Recorded version updated: 2025-03-23T13:04:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.00516", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.00516"}} @misc{arxiv_2405_00516, title = {{Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning}}, author = {{Lucas-Andreï Thil} and {Mirela Popa} and {Gerasimos Spanakis}}, year = {2024}, eprint = {2405.00516v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.00516v1}, note = {First published: 2024-05-01; Recorded arXiv version: v1; Recorded version updated: 2024-05-01T13:51:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.04497", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.04497"}} @misc{arxiv_2405_04497, title = {{Unveiling Disparities in Web Task Handling Between Human and Web Agent}}, author = {{Kihoon Son} and {Jinhyeon Kwon} and {DaEun Choi} and {Tae Soo Kim} and {Young-Ho Kim} and {Sangdoo Yun} and {Juho Kim}}, year = {2024}, eprint = {2405.04497v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.04497v2}, note = {First published: 2024-05-07; Recorded arXiv version: v2; Recorded version updated: 2024-05-08T05:44:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.07090", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.07090"}} @misc{arxiv_2405_07090, title = {{MUD: Towards a Large-Scale and Noise-Filtered UI Dataset for Modern Style UI Modeling}}, author = {{Sidong Feng} and {Suyu Ma} and {Han Wang} and {David Kong} and {Chunyang Chen}}, year = {2024}, eprint = {2405.07090v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.07090v1}, note = {First published: 2024-05-11; Recorded arXiv version: v1; Recorded version updated: 2024-05-11T20:32:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.11120", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.11120"}} @misc{arxiv_2405_11120, title = {{Latent State Estimation Helps UI Agents to Reason}}, author = {{William E Bishop} and {Alice Li} and {Christopher Rawles} and {Oriana Riva}}, year = {2024}, eprint = {2405.11120v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.11120v1}, note = {First published: 2024-05-17; Recorded arXiv version: v1; Recorded version updated: 2024-05-17T23:27:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.12842", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.12842"}} @misc{arxiv_2405_12842, title = {{SmartFlow: Robotic Process Automation using LLMs}}, author = {{Arushi Jain} and {Shubham Paliwal} and {Monika Sharma} and {Lovekesh Vig} and {Gautam Shroff}}, year = {2024}, eprint = {2405.12842v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.12842v1}, note = {First published: 2024-05-21; Recorded arXiv version: v1; Recorded version updated: 2024-05-21T14:49:12Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2405.14573", "catalog_id": "arxiv:2405.14573", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2405.14573"}, "publication": {"authors": ["Chris Rawles", "Sarah Clinckemaillie", "Yifan Chang", "Jonathan Waltz", "Gabrielle Lau", "Marybeth Fair", "Alice Li", "William Bishop", "Wei Li", "Folawiyo Campbell-Ajala", "Daniel Toyama", "Robert Berry", "Divya Tyamagundlu", "Timothy Lillicrap", "Oriana Riva"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "406-441", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/01a83bc2f2732a58e6aa731e659e7101-Paper-Conference.pdf", "publisher": null, "series": null, "title": "AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/01a83bc2f2732a58e6aa731e659e7101-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2405_14573, title = {{AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents}}, author = {{Christopher Rawles} and {Sarah Clinckemaillie} and {Yifan Chang} and {Jonathan Waltz} and {Gabrielle Lau} and {Marybeth Fair} and {Alice Li} and {William Bishop} and {Wei Li} and {Folawiyo Campbell-Ajala} and {Daniel Toyama} and {Robert Berry} and {Divya Tyamagundlu} and {Timothy Lillicrap} and {Oriana Riva}}, year = {2024}, eprint = {2405.14573v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.14573v5}, note = {First published: 2024-05-23; Recorded arXiv version: v5; Recorded version updated: 2025-04-06T20:37:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.15341", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.15341"}} @misc{arxiv_2405_15341, title = {{V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM}}, author = {{Abdur Rahman} and {Rajat Chawla} and {Muskaan Kumar} and {Arkajit Datta} and {Adarsh Jha} and {Mukunda NS} and {Ishaan Bhola}}, year = {2024}, eprint = {2405.15341v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.15341v2}, note = {First published: 2024-05-24; Recorded arXiv version: v2; Recorded version updated: 2024-07-21T07:34:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2405.20309", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2405.20309"}} @misc{arxiv_2405_20309, title = {{Large Language Models Can Self-Improve At Web Agent Tasks}}, author = {{Ajay Patel} and {Markus Hofmarcher} and {Claudiu Leoveanu-Condrei} and {Marius-Constantin Dinu} and {Chris Callison-Burch} and {Sepp Hochreiter}}, year = {2024}, eprint = {2405.20309v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.20309v2}, note = {First published: 2024-05-30; Recorded arXiv version: v2; Recorded version updated: 2024-10-01T21:28:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.01014", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.01014"}} @misc{arxiv_2406_01014, title = {{Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration}}, author = {{Junyang Wang} and {Haiyang Xu} and {Haitao Jia} and {Xi Zhang} and {Ming Yan} and {Weizhou Shen} and {Ji Zhang} and {Fei Huang} and {Jitao Sang}}, year = {2024}, eprint = {2406.01014v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.01014v1}, note = {First published: 2024-06-03; Recorded arXiv version: v1; Recorded version updated: 2024-06-03T05:50:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.01623", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.01623"}} @misc{arxiv_2406_01623, title = {{WebSuite: Systematically Evaluating Why Web Agents Fail}}, author = {{Eric Li} and {Jim Waldo}}, year = {2024}, eprint = {2406.01623v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.01623v1}, note = {First published: 2024-06-01; Recorded arXiv version: v1; Recorded version updated: 2024-06-01T00:32:26Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2406.03679", "catalog_id": "arxiv:2406.03679", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.03679"}, "publication": {"authors": ["Wei Li", "William Bishop", "Alice Li", "Chris Rawles", "Folawiyo Campbell-Ajala", "Divya Tyamagundlu", "Oriana Riva"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-2925", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "92130-92154", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a79f3ef3b445fd4659f44648f7ea8ffd-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "On the Effects of Data Scale on UI Control Agents", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a79f3ef3b445fd4659f44648f7ea8ffd-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2406_03679, title = {{On the Effects of Data Scale on UI Control Agents}}, author = {{Wei Li} and {William Bishop} and {Alice Li} and {Chris Rawles} and {Folawiyo Campbell-Ajala} and {Divya Tyamagundlu} and {Oriana Riva}}, year = {2024}, eprint = {2406.03679v6}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.03679v6}, note = {First published: 2024-06-06; Recorded arXiv version: v6; Recorded version updated: 2024-11-13T16:42:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.06947", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.06947"}} @misc{arxiv_2406_06947, title = {{CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only}}, author = {{Junhee Cho} and {Jihoon Kim} and {Daseul Bae} and {Jinho Choo} and {Youngjune Gwon} and {Yeong-Dae Kwon}}, year = {2024}, eprint = {2406.06947v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.06947v3}, note = {First published: 2024-06-11; Recorded arXiv version: v3; Recorded version updated: 2024-12-26T11:02:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.07822", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.07822"}} @misc{arxiv_2406_07822, title = {{Tell Me What's Next: Textual Foresight for Generic UI Representations}}, author = {{Andrea Burns} and {Kate Saenko} and {Bryan A. Plummer}}, year = {2024}, eprint = {2406.07822v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.07822v2}, note = {First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2024-08-08T02:36:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.08184", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.08184"}} @misc{arxiv_2406_08184, title = {{MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents}}, author = {{Luyuan Wang} and {Yongyu Deng} and {Yiwei Zha} and {Guodong Mao} and {Qinmin Wang} and {Tianchen Min} and {Wei Chen} and {Shoufa Chen}}, year = {2024}, eprint = {2406.08184v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.08184v1}, note = {First published: 2024-06-12; Recorded arXiv version: v1; Recorded version updated: 2024-06-12T13:14:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.08340", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.08340"}} @misc{arxiv_2406_08340, title = {{Practical, Automated Scenario-based Mobile App Testing}}, author = {{Shengcheng Yu} and {Chunrong Fang} and {Mingzhe Du} and {Zimin Ding} and {Zhenyu Chen} and {Zhendong Su}}, year = {2024}, eprint = {2406.08340v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.08340v1}, note = {First published: 2024-06-12; Recorded arXiv version: v1; Recorded version updated: 2024-06-12T15:48:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.08451", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.08451"}} @misc{arxiv_2406_08451, title = {{GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices}}, author = {{Quanfeng Lu} and {Wenqi Shao} and {Zitao Liu} and {Lingxiao Du} and {Fanqing Meng} and {Boxuan Li} and {Botong Chen} and {Siyuan Huang} and {Kaipeng Zhang} and {Ping Luo}}, year = {2024}, eprint = {2406.08451v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.08451v2}, note = {First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2025-08-01T03:37:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.09187", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2406.09187"}} @misc{arxiv_2406_09187, title = {{GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning}}, author = {{Zhen Xiang} and {Linzhi Zheng} and {Yanjie Li} and {Junyuan Hong} and {Qinbin Li} and {Han Xie} and {Jiawei Zhang} and {Zidi Xiong} and {Chulin Xie} and {Carl Yang} and {Dawn Song} and {Bo Li}}, year = {2024}, eprint = {2406.09187v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.09187v3}, note = {First published: 2024-06-13; Recorded arXiv version: v3; Recorded version updated: 2025-05-29T03:09:05Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2406.10227", "catalog_id": "arxiv:2406.10227", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.10227"}, "publication": {"authors": ["Kevin Q. Lin", "Linjie Li", "Difei Gao", "Qinchen Wu", "Mingyi Yan", "Zhengyuan Yang", "Lijuan Wang", "Mike Z. Shou"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-2214", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "69329-69360", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/804e757b7d7043c26701c3a313032101-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "VideoGUI: A Benchmark for GUI Automation from Instructional Videos", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2406_10227, title = {{VideoGUI: A Benchmark for GUI Automation from Instructional Videos}}, author = {{Kevin Qinghong Lin} and {Linjie Li} and {Difei Gao} and {Qinchen WU} and {Mingyi Yan} and {Zhengyuan Yang} and {Lijuan Wang} and {Mike Zheng Shou}}, year = {2024}, eprint = {2406.10227v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.10227v1}, note = {First published: 2024-06-14; Recorded arXiv version: v1; Recorded version updated: 2024-06-14T17:59:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.10819", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.10819"}} @misc{arxiv_2406_10819, title = {{GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding}}, author = {{Dongping Chen} and {Yue Huang} and {Siyuan Wu} and {Jingyu Tang} and {Liuyi Chen} and {Yilin Bai} and {Zhigang He} and {Chenlong Wang} and {Huichi Zhou} and {Yiqiang Li} and {Tianshuo Zhou} and {Yue Yu} and {Chujie Gao} and {Qihui Zhang} and {Yi Gui} and {Zhen Li} and {Yao Wan} and {Pan Zhou} and {Jianfeng Gao} and {Lichao Sun}}, year = {2024}, eprint = {2406.10819v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.10819v2}, note = {First published: 2024-06-16; Recorded arXiv version: v2; Recorded version updated: 2025-03-24T11:46:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.11317", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.11317"}} @misc{arxiv_2406_11317, title = {{GUICourse: From General Vision Language Models to Versatile GUI Agents}}, author = {{Wentong Chen} and {Junbo Cui} and {Jinyi Hu} and {Yujia Qin} and {Junjie Fang} and {Yue Zhao} and {Chongyi Wang} and {Jun Liu} and {Guirong Chen} and {Yupeng Huo} and {Yuan Yao} and {Yankai Lin} and {Zhiyuan Liu} and {Maosong Sun}}, year = {2024}, eprint = {2406.11317v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.11317v2}, note = {First published: 2024-06-17; Recorded arXiv version: v2; Recorded version updated: 2025-05-30T07:30:07Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2406.11896", "catalog_id": "arxiv:2406.11896", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.11896"}, "publication": {"authors": ["Hao Bai", "Yifei Zhou", "Mert Cemri", "Jiayi Pan", "Alane Suhr", "Sergey Levine", "Aviral Kumar"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-0397", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "12461-12495", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/1704ddd0bb89f159dfe609b32c889995-Paper-Conference.pdf", "publisher": null, "series": null, "title": "DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2406_11896, title = {{DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning}}, author = {{Hao Bai} and {Yifei Zhou} and {Mert Cemri} and {Jiayi Pan} and {Alane Suhr} and {Sergey Levine} and {Aviral Kumar}}, year = {2024}, eprint = {2406.11896v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.11896v1}, note = {First published: 2024-06-14; Recorded arXiv version: v1; Recorded version updated: 2024-06-14T17:49:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.12373", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.12373"}} @misc{arxiv_2406_12373, title = {{WebCanvas: Benchmarking Web Agents in Online Environments}}, author = {{Yichen Pan} and {Dehan Kong} and {Sida Zhou} and {Cheng Cui} and {Yifei Leng} and {Bing Jiang} and {Hangyu Liu} and {Yanyi Shang} and {Shuyan Zhou} and {Tongshuang Wu} and {Zhengyang Wu}}, year = {2024}, eprint = {2406.12373v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.12373v3}, note = {First published: 2024-06-18; Recorded arXiv version: v3; Recorded version updated: 2024-07-16T06:19:21Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2406.12814", "catalog_id": "arxiv:2406.12814", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.12814"}, "publication": {"authors": ["Chen Wu", "Rishi Shah", "Jing Yu Koh", "Russ Salakhutdinov", "Daniel Fried", "Aditi Raghunathan"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/460a1d8eac34125dad453b28d6d64446-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "28362-28383", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/460a1d8eac34125dad453b28d6d64446-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Dissecting Adversarial Robustness of Multimodal LM Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/460a1d8eac34125dad453b28d6d64446-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2406_12814, title = {{Dissecting Adversarial Robustness of Multimodal LM Agents}}, author = {{Chen Henry Wu} and {Rishi Shah} and {Jing Yu Koh} and {Ruslan Salakhutdinov} and {Daniel Fried} and {Aditi Raghunathan}}, year = {2024}, eprint = {2406.12814v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.12814v3}, note = {First published: 2024-06-18; Recorded arXiv version: v3; Recorded version updated: 2025-02-04T20:02:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.13264", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.13264"}} @misc{arxiv_2406_13264, title = {{WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks}}, author = {{Michael Wornow} and {Avanika Narayan} and {Ben Viggiano} and {Ishan S. Khare} and {Tathagat Verma} and {Tibor Thompson} and {Miguel Angel Fuentes Hernandez} and {Sudharsan Sundar} and {Chloe Trujillo} and {Krrish Chawla} and {Rongfei Lu} and {Justin Shen} and {Divya Nagaraj} and {Joshua Martinez} and {Vardhan Agrawal} and {Althea Hudson} and {Nigam H. Shah} and {Christopher Re}}, year = {2024}, eprint = {2406.13264v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.13264v2}, note = {First published: 2024-06-19; Recorded arXiv version: v2; Recorded version updated: 2024-10-11T00:06:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.13719", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.13719"}} @misc{arxiv_2406_13719, title = {{GUI Action Narrator: Where and When Did That Action Take Place?}}, author = {{Qinchen Wu} and {Difei Gao} and {Kevin Qinghong Lin} and {Zhuoyu Wu} and {Xiangwu Guo} and {Peiran Li} and {Weichen Zhang} and {Hengxu Wang} and {Mike Zheng Shou}}, year = {2024}, eprint = {2406.13719v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.13719v1}, note = {First published: 2024-06-19; Recorded arXiv version: v1; Recorded version updated: 2024-06-19T17:22:11Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2406.14056", "catalog_id": "arxiv:2406.14056", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.14056"}, "publication": {"authors": ["Meng Ziyang", "Yu Dai", "Zezheng Gong", "Shaoxiong Guo", "Minglong Tang", "Tongquan Wei"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.findings-emnlp.68", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-emnlp.68/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "1261-1279", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.68.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.68/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null}} @misc{arxiv_2406_14056, title = {{VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning}}, author = {{Ziyang Meng} and {Yu Dai} and {Zezheng Gong} and {Shaoxiong Guo} and {Minglong Tang} and {Tongquan Wei}}, year = {2024}, eprint = {2406.14056v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.14056v3}, note = {First published: 2024-06-20; Recorded arXiv version: v3; Recorded version updated: 2024-11-04T09:31:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.14250", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.14250"}} @misc{arxiv_2406_14250, title = {{E-ANT: A Large-Scale Dataset for Efficient Automatic GUI NavigaTion}}, author = {{Ke Wang} and {Tianyu Xia} and {Zhangxuan Gu} and {Yi Zhao} and {Shuheng Shen} and {Changhua Meng} and {Weiqiang Wang} and {Ke Xu}}, year = {2024}, eprint = {2406.14250v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.14250v3}, note = {First published: 2024-06-20; Recorded arXiv version: v3; Recorded version updated: 2024-07-01T08:37:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2406.14314", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.14314"}} @misc{arxiv_2406_14314, title = {{Identifying User Goals from UI Trajectories}}, author = {{Omri Berkovitch} and {Sapir Caduri} and {Noam Kahlon} and {Anatoly Efros} and {Avi Caciularu} and {Ido Dagan}}, year = {2024}, eprint = {2406.14314v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.14314v3}, note = {First published: 2024-06-20; Recorded arXiv version: v3; Recorded version updated: 2025-03-03T15:47:10Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2406.19263", "catalog_id": "arxiv:2406.19263", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.19263"}, "publication": {"authors": ["Yue Fan", "Lei Ding", "Ching-Chen Kuo", "Shan Jiang", "Yang Zhao", "Xinze Guan", "Jie Yang", "Yi Zhang", "Xin Eric Wang"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.emnlp-main.533", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.emnlp-main.533/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "9503-9522", "pdf_url": "https://aclanthology.org/2024.emnlp-main.533.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding", "type": "conference-paper", "url": "https://aclanthology.org/2024.emnlp-main.533/", "venue": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", "volume": null}} @misc{arxiv_2406_19263, title = {{Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding}}, author = {{Yue Fan} and {Lei Ding} and {Ching-Chen Kuo} and {Shan Jiang} and {Yang Zhao} and {Xinze Guan} and {Jie Yang} and {Yi Zhang} and {Xin Eric Wang}}, year = {2024}, eprint = {2406.19263v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.19263v2}, note = {First published: 2024-06-27; Recorded arXiv version: v2; Recorded version updated: 2024-10-25T18:16:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.00993", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.00993"}} @misc{arxiv_2407_00993, title = {{Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents}}, author = {{Shihan Deng} and {Weikai Xu} and {Hongda Sun} and {Wei Liu} and {Tao Tan} and {Jianfeng Liu} and {Ang Li} and {Jian Luan} and {Bin Wang} and {Rui Yan} and {Shuo Shang}}, year = {2024}, eprint = {2407.00993v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.00993v1}, note = {First published: 2024-07-01; Recorded arXiv version: v1; Recorded version updated: 2024-07-01T06:10:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.01476", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.01476"}} @misc{arxiv_2407_01476, title = {{Tree Search for Language Model Agents}}, author = {{Jing Yu Koh} and {Stephen McAleer} and {Daniel Fried} and {Ruslan Salakhutdinov}}, year = {2024}, eprint = {2407.01476v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.01476v4}, note = {First published: 2024-07-01; Recorded arXiv version: v4; Recorded version updated: 2026-02-08T15:06:40Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2407.01511", "catalog_id": "arxiv:2407.01511", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2407.01511"}, "publication": {"authors": ["Tianqi Xu", "Linyao Chen", "Dai-Jie Wu", "Yanjun Chen", "Zecheng Zhang", "Xiang Yao", "Zhiqiang Xie (\u8c22\u5fd7\u5f3a)", "Yongchao Chen", "Shilong Liu", "Bochen Qian", "Anjie Yang", "Zhaoxuan Jin", "Jianbo Deng", "Philip Torr", "Bernard Ghanem", "Guohao Li"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.1113", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.1113/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "21607-21647", "pdf_url": "https://aclanthology.org/2025.findings-acl.1113.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.1113/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2407_01511, title = {{CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents}}, author = {{Tianqi Xu} and {Linyao Chen} and {Dai-Jie Wu} and {Yanjun Chen} and {Zecheng Zhang} and {Xiang Yao} and {Zhiqiang Xie} and {Yongchao Chen} and {Shilong Liu} and {Bochen Qian} and {Anjie Yang} and {Zhaoxuan Jin} and {Jianbo Deng} and {Philip Torr} and {Bernard Ghanem} and {Guohao Li}}, year = {2024}, eprint = {2407.01511v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.01511v4}, note = {First published: 2024-07-01; Recorded arXiv version: v4; Recorded version updated: 2025-07-20T13:42:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.01558", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.01558"}} @misc{arxiv_2407_01558, title = {{Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces}}, author = {{El Hassane Ettifouri} and {Jessica López Espejel} and {Laura Minkova} and {Tassnim Dardouri} and {Walid Dahhane}}, year = {2024}, eprint = {2407.01558v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.01558v3}, note = {First published: 2024-05-05; Recorded arXiv version: v3; Recorded version updated: 2025-07-18T11:35:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.03037", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.03037"}} @misc{arxiv_2407_03037, title = {{Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile Apps}}, author = {{Zhe Liu} and {Cheng Li} and {Chunyang Chen} and {Junjie Wang} and {Mengzhuo Chen} and {Boyu Wu} and {Yawen Wang} and {Jun Hu} and {Qing Wang}}, year = {2024}, eprint = {2407.03037v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.03037v2}, note = {First published: 2024-07-03; Recorded arXiv version: v2; Recorded version updated: 2024-12-04T08:00:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.03913", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.03913"}} @misc{arxiv_2407_03913, title = {{MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices}}, author = {{Jiayi Zhang} and {Chuang Zhao} and {Yihan Zhao} and {Zhaoyang Yu} and {Ming He} and {Jianping Fan}}, year = {2024}, eprint = {2407.03913v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.03913v1}, note = {First published: 2024-07-04; Recorded arXiv version: v1; Recorded version updated: 2024-07-04T13:12:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.04346", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.04346"}} @misc{arxiv_2407_04346, title = {{MobileFlow: A Multimodal LLM For Mobile GUI Agent}}, author = {{Songqin Nong} and {Jiali Zhu} and {Rui Wu} and {Jiongchao Jin} and {Shuo Shan} and {Xiutian Huang} and {Wenhao Xu}}, year = {2024}, eprint = {2407.04346v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.04346v3}, note = {First published: 2024-07-05; Recorded arXiv version: v3; Recorded version updated: 2024-12-06T07:43:34Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2407.05291", "catalog_id": "arxiv:2407.05291", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2407.05291"}, "publication": {"authors": ["L\u00e9o Boisvert", "Megh Thakkar", "Maxime Gasse", "Massimo Caccia", "Thibault L. De Chezelles", "Quentin Cappart", "Nicolas Chapados", "Alexandre Lacoste", "Alexandre Drouin"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-0195", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/0b82662b6c32e887bb252a74d8cb2d5e-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "5996-6051", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/0b82662b6c32e887bb252a74d8cb2d5e-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/0b82662b6c32e887bb252a74d8cb2d5e-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2407_05291, title = {{WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks}}, author = {{Léo Boisvert} and {Megh Thakkar} and {Maxime Gasse} and {Massimo Caccia} and {Thibault Le Sellier De Chezelles} and {Quentin Cappart} and {Nicolas Chapados} and {Alexandre Lacoste} and {Alexandre Drouin}}, year = {2024}, eprint = {2407.05291v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.05291v2}, note = {First published: 2024-07-07; Recorded arXiv version: v2; Recorded version updated: 2025-02-05T21:50:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.08850", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2407.08850"}} @misc{arxiv_2407_08850, title = {{UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset}}, author = {{Peitong Duan} and {Chin-yi Chen} and {Gang Li} and {Bjoern Hartmann} and {Yang Li}}, year = {2024}, eprint = {2407.08850v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.08850v3}, note = {First published: 2024-07-11; Recorded arXiv version: v3; Recorded version updated: 2024-08-13T23:41:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.09018", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.09018"}} @misc{arxiv_2407_09018, title = {{AUITestAgent: Automatic Requirements Oriented GUI Function Testing}}, author = {{Yongxiang Hu} and {Xuan Wang} and {Yingchuan Wang} and {Yu Zhang} and {Shiyu Guo} and {Chaoyi Chen} and {Xin Wang} and {Yangfan Zhou}}, year = {2024}, eprint = {2407.09018v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.09018v1}, note = {First published: 2024-07-12; Recorded arXiv version: v1; Recorded version updated: 2024-07-12T06:14:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.09295", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.09295"}} @misc{arxiv_2407_09295, title = {{Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents}}, author = {{Yulong Yang} and {Xinshan Yang} and {Shuaidong Li} and {Chenhao Lin} and {Zhengyu Zhao} and {Chao Shen} and {Tianwei Zhang}}, year = {2024}, eprint = {2407.09295v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.09295v3}, note = {First published: 2024-07-12; Recorded arXiv version: v3; Recorded version updated: 2025-03-16T07:13:53Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2407.10956", "catalog_id": "arxiv:2407.10956", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2407.10956"}, "publication": {"authors": ["Ruisheng Cao", "Fangyu Lei", "Haoyuan Wu", "Jixuan Chen", "Yeqiao Fu", "Hongcheng Gao", "Xinzhuang Xiong", "Hanchong Zhang", "Yuchen Mao", "Wenjing Hu", "Tianbao Xie", "Hongshen Xu", "Danyang Zhang", "Sida Wang", "Ruoxi Sun", "Pengcheng Yin", "Caiming Xiong", "Ansong Ni", "Qian Liu", "Victor Zhong", "Lu Chen", "Kai Yu", "Tao Yu"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-3421", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "107703-107744", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/c2f71567cd53464161cab3336e8fc865-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2407_10956, title = {{Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?}}, author = {{Ruisheng Cao} and {Fangyu Lei} and {Haoyuan Wu} and {Jixuan Chen} and {Yeqiao Fu} and {Hongcheng Gao} and {Xinzhuang Xiong} and {Hanchong Zhang} and {Yuchen Mao} and {Wenjing Hu} and {Tianbao Xie} and {Hongshen Xu} and {Danyang Zhang} and {Sida Wang} and {Ruoxi Sun} and {Pengcheng Yin} and {Caiming Xiong} and {Ansong Ni} and {Qian Liu} and {Victor Zhong} and {Lu Chen} and {Kai Yu} and {Tao Yu}}, year = {2024}, eprint = {2407.10956v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.10956v1}, note = {First published: 2024-07-15; Recorded arXiv version: v1; Recorded version updated: 2024-07-15T17:54:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.13032", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.13032"}} @misc{arxiv_2407_13032, title = {{Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems}}, author = {{Tamer Abuelsaad} and {Deepak Akkil} and {Prasenjit Dey} and {Ashish Jagmohan} and {Aditya Vempaty} and {Ravi Kokku}}, year = {2024}, eprint = {2407.13032v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.13032v1}, note = {First published: 2024-07-17; Recorded arXiv version: v1; Recorded version updated: 2024-07-17T21:44:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.15673", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.15673"}} @misc{arxiv_2407_15673, title = {{IDA: Breaking Barriers in No-code UI Automation Through Large Language Models and Human-Centric Design}}, author = {{Segev Shlomov} and {Avi Yaeli} and {Sami Marreed} and {Sivan Schwartz} and {Netanel Eder} and {Offer Akrabi} and {Sergey Zeltyn}}, year = {2024}, eprint = {2407.15673v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.15673v3}, note = {First published: 2024-07-22; Recorded arXiv version: v3; Recorded version updated: 2024-08-18T09:02:43Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2407.15711", "catalog_id": "arxiv:2407.15711", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2407.15711"}, "publication": {"authors": ["Ori Yoran", "Samuel Joseph Amouyal", "Chaitanya Malaviya", "Ben Bogin", "Ofir Press", "Jonathan Berant"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.emnlp-main.505", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.emnlp-main.505/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "8938-8968", "pdf_url": "https://aclanthology.org/2024.emnlp-main.505.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?", "type": "conference-paper", "url": "https://aclanthology.org/2024.emnlp-main.505/", "venue": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", "volume": null}} @misc{arxiv_2407_15711, title = {{AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?}}, author = {{Ori Yoran} and {Samuel Joseph Amouyal} and {Chaitanya Malaviya} and {Ben Bogin} and {Ofir Press} and {Jonathan Berant}}, year = {2024}, eprint = {2407.15711v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.15711v2}, note = {First published: 2024-07-22; Recorded arXiv version: v2; Recorded version updated: 2024-10-21T15:45:31Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2407.17490", "catalog_id": "arxiv:2407.17490", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2407.17490"}, "publication": {"authors": ["Yuxiang Chai", "Siyuan Huang", "Yazhe Niu", "Han Xiao", "Liang Liu", "Guozhi Wang", "Dingyu Zhang", "Shuai Ren", "Hongsheng Li"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.110", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.110/", "https://aclanthology.org/2025.findings-acl.110.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, lists nine authors including Guozhi Wang; the retained arXiv snapshot lists eight. Each edition retains its own authors.", "pages": "2138-2156", "pdf_url": "https://aclanthology.org/2025.findings-acl.110.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.110/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2407_17490, title = {{AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents}}, author = {{Yuxiang Chai} and {Siyuan Huang} and {Yazhe Niu} and {Han Xiao} and {Liang Liu} and {Dingyu Zhang} and {Shuai Ren} and {Hongsheng Li}}, year = {2024}, eprint = {2407.17490v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.17490v2}, note = {First published: 2024-07-03; Recorded arXiv version: v2; Recorded version updated: 2025-05-29T02:43:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.18901", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2407.18901"}} @misc{arxiv_2407_18901, title = {{AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents}}, author = {{Harsh Trivedi} and {Tushar Khot} and {Mareike Hartmann} and {Ruskin Manku} and {Vinty Dong} and {Edward Li} and {Shashank Gupta} and {Ashish Sabharwal} and {Niranjan Balasubramanian}}, year = {2024}, eprint = {2407.18901v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.18901v1}, note = {First published: 2024-07-26; Recorded arXiv version: v1; Recorded version updated: 2024-07-26T17:55:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2407.19056", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.19056"}} @misc{arxiv_2407_19056, title = {{OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation}}, author = {{Zilong Wang} and {Yuedong Cui} and {Li Zhong} and {Zimin Zhang} and {Da Yin} and {Bill Yuchen Lin} and {Jingbo Shang}}, year = {2024}, eprint = {2407.19056v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.19056v1}, note = {First published: 2024-07-26; Recorded arXiv version: v1; Recorded version updated: 2024-07-26T19:27:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2408.00203", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2408.00203"}} @misc{arxiv_2408_00203, title = {{OmniParser for Pure Vision Based GUI Agent}}, author = {{Yadong Lu} and {Jianwei Yang} and {Yelong Shen} and {Ahmed Awadallah}}, year = {2024}, eprint = {2408.00203v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.00203v1}, note = {First published: 2024-08-01; Recorded arXiv version: v1; Recorded version updated: 2024-08-01T00:00:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2408.02544", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2408.02544"}} @misc{arxiv_2408_02544, title = {{Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions}}, author = {{Xinbei Ma} and {Yiting Wang} and {Yao Yao} and {Tongxin Yuan} and {Aston Zhang} and {Zhuosheng Zhang} and {Hai Zhao}}, year = {2024}, eprint = {2408.02544v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.02544v3}, note = {First published: 2024-08-05; Recorded arXiv version: v3; Recorded version updated: 2025-09-05T09:21:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2408.06327", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2408.06327"}} @misc{arxiv_2408_06327, title = {{VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents}}, author = {{Xiao Liu} and {Tianjie Zhang} and {Yu Gu} and {Iat Long Iong} and {Yifan Xu} and {Xixuan Song} and {Shudan Zhang} and {Hanyu Lai} and {Xinyi Liu} and {Hanlin Zhao} and {Jiadai Sun} and {Xinyue Yang} and {Yu Yang} and {Zehan Qi} and {Shuntian Yao} and {Xueqiao Sun} and {Siyi Cheng} and {Qinkai Zheng} and {Hao Yu} and {Hanchen Zhang} and {Wenyi Hong} and {Ming Ding} and {Lihang Pan} and {Xiaotao Gu} and {Aohan Zeng} and {Zhengxiao Du} and {Chan Hee Song} and {Yu Su} and {Yuxiao Dong} and {Jie Tang}}, year = {2024}, eprint = {2408.06327v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.06327v1}, note = {First published: 2024-08-12; Recorded arXiv version: v1; Recorded version updated: 2024-08-12T17:44:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2408.11824", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2408.11824"}} @misc{arxiv_2408_11824, title = {{AppAgent v2: Advanced Agent for Flexible Mobile Interactions}}, author = {{Yanda Li} and {Chi Zhang} and {Wenjia Jiang} and {Wanqi Yang} and {Bin Fu} and {Pei Cheng} and {Xin Chen} and {Ling Chen} and {Yunchao Wei}}, year = {2024}, eprint = {2408.11824v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.11824v4}, note = {First published: 2024-08-05; Recorded arXiv version: v4; Recorded version updated: 2025-09-17T09:06:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2408.15978", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2408.15978"}} @misc{arxiv_2408_15978, title = {{WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration}}, author = {{Yao Zhang} and {Zijian Ma} and {Yunpu Ma} and {Zhen Han} and {Yu Wu} and {Volker Tresp}}, year = {2024}, eprint = {2408.15978v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.15978v1}, note = {First published: 2024-08-28; Recorded arXiv version: v1; Recorded version updated: 2024-08-28T17:49:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.01927", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.01927"}} @misc{arxiv_2409_01927, title = {{From Grounding to Planning: Benchmarking Bottlenecks in Web Agents}}, author = {{Segev Shlomov} and {Ben wiesel} and {Aviad Sela} and {Ido Levy} and {Liane Galanti} and {Roy Abitbol}}, year = {2024}, eprint = {2409.01927v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.01927v1}, note = {First published: 2024-09-03; Recorded arXiv version: v1; Recorded version updated: 2024-09-03T14:17:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.07429", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.07429"}} @misc{arxiv_2409_07429, title = {{Agent Workflow Memory}}, author = {{Zora Zhiruo Wang} and {Jiayuan Mao} and {Daniel Fried} and {Graham Neubig}}, year = {2024}, eprint = {2409.07429v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.07429v1}, note = {First published: 2024-09-11; Recorded arXiv version: v1; Recorded version updated: 2024-09-11T17:21:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.08264", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.08264"}} @misc{arxiv_2409_08264, title = {{Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale}}, author = {{Rogerio Bonatti} and {Dan Zhao} and {Francesco Bonacci} and {Dillon Dupont} and {Sara Abdali} and {Yinheng Li} and {Yadong Lu} and {Justin Wagle} and {Kazuhito Koishida} and {Arthur Bucker} and {Lawrence Jang} and {Zack Hui}}, year = {2024}, eprint = {2409.08264v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.08264v2}, note = {First published: 2024-09-12; Recorded arXiv version: v2; Recorded version updated: 2024-09-13T20:17:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.09354", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.09354"}} @misc{arxiv_2409_09354, title = {{PeriGuru: A Peripheral Robotic Mobile App Operation Assistant based on GUI Image Understanding and Prompting with LLM}}, author = {{Kelin Fu} and {Yang Tian} and {Kaigui Bian}}, year = {2024}, eprint = {2409.09354v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.09354v1}, note = {First published: 2024-09-14; Recorded arXiv version: v1; Recorded version updated: 2024-09-14T07:54:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.10741", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.10741"}} @misc{arxiv_2409_10741, title = {{NaviQAte: Functionality-Guided Web Application Navigation}}, author = {{Mobina Shahbandeh} and {Parsa Alian} and {Noor Nashid} and {Ali Mesbah}}, year = {2024}, eprint = {2409.10741v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.10741v1}, note = {First published: 2024-09-16; Recorded arXiv version: v1; Recorded version updated: 2024-09-16T21:18:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.10811", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.10811"}} @misc{arxiv_2409_10811, title = {{Grounded GUI Understanding for Vision-Based Spatial Intelligent Agent: Exemplified by Extended Reality Apps}}, author = {{Shuqing Li} and {Binchang Li} and {Yepang Liu} and {Cuiyun Gao} and {Jianping Zhang} and {Shing-Chi Cheung} and {Michael R. Lyu}}, year = {2024}, eprint = {2409.10811v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.10811v4}, note = {First published: 2024-09-17; Recorded arXiv version: v4; Recorded version updated: 2025-10-01T17:58:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.11295", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.11295"}} @misc{arxiv_2409_11295, title = {{EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage}}, author = {{Zeyi Liao} and {Lingbo Mo} and {Chejian Xu} and {Mintong Kang} and {Jiawei Zhang} and {Chaowei Xiao} and {Yuan Tian} and {Bo Li} and {Huan Sun}}, year = {2024}, eprint = {2409.11295v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.11295v5}, note = {First published: 2024-09-17; Recorded arXiv version: v5; Recorded version updated: 2025-03-12T20:54:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.12089", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.12089"}} @misc{arxiv_2409_12089, title = {{The Impact of Element Ordering on LM Agent Performance}}, author = {{Wayne Chi} and {Ameet Talwalkar} and {Chris Donahue}}, year = {2024}, eprint = {2409.12089v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.12089v3}, note = {First published: 2024-09-18; Recorded arXiv version: v3; Recorded version updated: 2024-10-06T21:25:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.13711", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.13711"}} @misc{arxiv_2409_13711, title = {{WebQuest: A Benchmark for Multimodal QA on Web Page Sequences}}, author = {{Maria Wang} and {Srinivas Sunkara} and {Gilles Baechler} and {Jason Lin} and {Yun Zhu} and {Fedir Zubach} and {Lei Shu} and {Jindong Chen}}, year = {2024}, eprint = {2409.13711v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.13711v2}, note = {First published: 2024-09-06; Recorded arXiv version: v2; Recorded version updated: 2024-09-24T18:38:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.14337", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.14337"}} @misc{arxiv_2409_14337, title = {{MobileViews: A Million-scale and Diverse Mobile GUI Dataset}}, author = {{Longxi Gao} and {Li Zhang} and {Shihe Wang} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Shangguang Wang} and {Yuanchun Li} and {Mengwei Xu}}, year = {2024}, eprint = {2409.14337v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.14337v3}, note = {First published: 2024-09-22; Recorded arXiv version: v3; Recorded version updated: 2025-11-25T02:43:11Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2409.14818", "catalog_id": "arxiv:2409.14818", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2409.14818"}, "publication": {"authors": ["Qinzhuo Wu", "Weikai Xu", "Wei Liu", "Tao Tan", "Jianfeng Liu", "Ang Li", "Jian Luan", "Bin Wang", "Shuo Shang"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.findings-emnlp.599", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-emnlp.599/", "https://aclanthology.org/2024.findings-emnlp.599.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. The landing page and its BibTeX list the fifth author as Liujian Liujianfeng; the PDF names Jianfeng Liu.", "pages": "10231-10251", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.599.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.599/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null}} @misc{arxiv_2409_14818, title = {{MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding}}, author = {{Qinzhuo Wu} and {Weikai Xu} and {Wei Liu} and {Tao Tan} and {Jianfeng Liu} and {Ang Li} and {Jian Luan} and {Bin Wang} and {Shuo Shang}}, year = {2024}, eprint = {2409.14818v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.14818v2}, note = {First published: 2024-09-23; Recorded arXiv version: v2; Recorded version updated: 2024-10-03T05:23:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.15441", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.15441"}} @misc{arxiv_2409_15441, title = {{Steward: Natural Language Web Automation}}, author = {{Brian Tang} and {Kang G. Shin}}, year = {2024}, eprint = {2409.15441v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.15441v1}, note = {First published: 2024-09-23; Recorded arXiv version: v1; Recorded version updated: 2024-09-23T18:06:32Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2409.15637", "catalog_id": "arxiv:2409.15637", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2409.15637"}, "publication": {"authors": ["Tianyue Ou", "Frank F. Xu", "Aman Madaan", "Jiarui Liu", "Robert Lo", "Abishek Sridhar", "Sudipta Sengupta", "Dan Roth", "Graham Neubig", "Shuyan Zhou"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-2908", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "91618-91652", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/a6a6891cf1dfc64d664f086cf5976e93-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/a6a6891cf1dfc64d664f086cf5976e93-Abstract-Conference.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}} @misc{arxiv_2409_15637, title = {{Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale}}, author = {{Tianyue Ou} and {Frank F. Xu} and {Aman Madaan} and {Jiarui Liu} and {Robert Lo} and {Abishek Sridhar} and {Sudipta Sengupta} and {Dan Roth} and {Graham Neubig} and {Shuyan Zhou}}, year = {2024}, eprint = {2409.15637v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.15637v2}, note = {First published: 2024-09-24; Recorded arXiv version: v2; Recorded version updated: 2024-11-27T16:34:52Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2409.17140", "catalog_id": "arxiv:2409.17140", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2409.17140"}, "publication": {"authors": ["Junting Lu", "Zhiyang Zhang", "Fangkai Yang", "Jue Zhang", "Lu Wang", "Chao Du", "Qingwei Lin", "Saravan Rajmohan", "Dongmei Zhang", "Qi Zhang"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.381", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.381/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "7711-7743", "pdf_url": "https://aclanthology.org/2025.acl-long.381.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.381/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2409_17140, title = {{AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents}}, author = {{Junting Lu} and {Zhiyang Zhang} and {Fangkai Yang} and {Jue Zhang} and {Lu Wang} and {Chao Du} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang} and {Qi Zhang}}, year = {2024}, eprint = {2409.17140v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.17140v2}, note = {First published: 2024-09-25; Recorded arXiv version: v2; Recorded version updated: 2025-05-19T16:12:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2409.18060", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2409.18060"}} @misc{arxiv_2409_18060, title = {{Inferring Alt-text For UI Icons With Large Language Models During App Development}}, author = {{Sabrina Haque} and {Christoph Csallner}}, year = {2024}, eprint = {2409.18060v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.18060v2}, note = {First published: 2024-09-26; Recorded arXiv version: v2; Recorded version updated: 2024-10-07T19:04:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.00079", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2410.00079"}} @misc{arxiv_2410_00079, title = {{Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface}}, author = {{Wenyue Hua} and {Mengting Wan} and {Shashank Vadrevu} and {Ryan Nadel} and {Yongfeng Zhang} and {Chi Wang}}, year = {2024}, eprint = {2410.00079v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.00079v1}, note = {First published: 2024-09-30; Recorded arXiv version: v1; Recorded version updated: 2024-09-30T16:52:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.00201", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.00201"}} @misc{arxiv_2410_00201, title = {{DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation}}, author = {{Yi-Hao Peng} and {Faria Huq} and {Yue Jiang} and {Jason Wu} and {Amanda Xin Yue Li} and {Jeffrey Bigham} and {Amy Pavel}}, year = {2024}, eprint = {2410.00201v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.00201v1}, note = {First published: 2024-09-30; Recorded arXiv version: v1; Recorded version updated: 2024-09-30T19:55:54Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.00467", "catalog_id": "arxiv:2410.00467", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.00467"}, "publication": {"authors": ["Shaoqing Zhang", "Zhuosheng Zhang", "Kehai Chen (\u9648\u79d1\u6d77)", "Xinbei Ma", "Muyun Yang (\u6768\u6c90\u6600)", "Tiejun Zhao (\u8d75\u94c1\u519b)", "Min Zhang"], "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 11], "doi": "10.18653/v1/2024.findings-emnlp.70", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2024.findings-emnlp.70/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "1304-1320", "pdf_url": "https://aclanthology.org/2024.findings-emnlp.70.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Dynamic Planning for LLM-based Graphical User Interface Automation", "type": "conference-paper", "url": "https://aclanthology.org/2024.findings-emnlp.70/", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024", "volume": null}} @misc{arxiv_2410_00467, title = {{Dynamic Planning for LLM-based Graphical User Interface Automation}}, author = {{Shaoqing Zhang} and {Zhuosheng Zhang} and {Kehai Chen} and {Xinbei Ma} and {Muyun Yang} and {Tiejun Zhao} and {Min Zhang}}, year = {2024}, eprint = {2410.00467v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.00467v3}, note = {First published: 2024-10-01; Recorded arXiv version: v3; Recorded version updated: 2024-12-19T14:29:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.00689", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.00689"}} @misc{arxiv_2410_00689, title = {{Multimodal Auto Validation For Self-Refinement in Web Agents}}, author = {{Ruhana Azam} and {Tamer Abuelsaad} and {Aditya Vempaty} and {Ashish Jagmohan}}, year = {2024}, eprint = {2410.00689v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.00689v2}, note = {First published: 2024-10-01; Recorded arXiv version: v2; Recorded version updated: 2024-10-11T15:42:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.02810", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2410.02810"}} @misc{arxiv_2410_02810, title = {{StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking}}, author = {{Nikolai Rozanov} and {Marek Rei}}, year = {2024}, eprint = {2410.02810v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.02810v3}, note = {First published: 2024-09-21; Recorded arXiv version: v3; Recorded version updated: 2025-04-08T06:37:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.02907", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.02907"}} @misc{arxiv_2410_02907, title = {{NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild}}, author = {{Shikhar Murty} and {Hao Zhu} and {Dzmitry Bahdanau} and {Christopher D. Manning}}, year = {2024}, eprint = {2410.02907v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.02907v2}, note = {First published: 2024-10-03; Recorded arXiv version: v2; Recorded version updated: 2025-02-05T18:56:51Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.05243", "catalog_id": "arxiv:2410.05243", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.05243"}, "publication": {"authors": ["Boyu Gou", "Demi Ruohan Wang", "Boyuan Zheng", "Yanan Xie", "Cheng Chang", "Yiheng Shu", "Huan Sun", "Yu Su"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "30851-30883", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/4ca0e369689dadb25a5345ba9755ad6f-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/4ca0e369689dadb25a5345ba9755ad6f-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2410_05243, title = {{Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents}}, author = {{Boyu Gou} and {Ruohan Wang} and {Boyuan Zheng} and {Yanan Xie} and {Cheng Chang} and {Yiheng Shu} and {Huan Sun} and {Yu Su}}, year = {2024}, eprint = {2410.05243v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.05243v3}, note = {First published: 2024-10-07; Recorded arXiv version: v3; Recorded version updated: 2025-06-17T15:06:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.06703", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.06703"}} @misc{arxiv_2410_06703, title = {{ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents}}, author = {{Ido Levy} and {Ben Wiesel} and {Sami Marreed} and {Alon Oved} and {Avi Yaeli} and {Nir Mashkif} and {Segev Shlomov}}, year = {2024}, eprint = {2410.06703v7}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.06703v7}, note = {First published: 2024-10-09; Recorded arXiv version: v7; Recorded version updated: 2026-06-04T09:59:28Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.08164", "catalog_id": "arxiv:2410.08164", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.08164"}, "publication": {"authors": ["Saaket Agashe", "Jiuzhou Han", "Shuyu Gan", "Jiachen Yang", "Ang Li", "Xin Wang"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/394c7c30ea87b5c3521b4d9e9d419071-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "22924-22946", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/394c7c30ea87b5c3521b4d9e9d419071-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Agent S: An Open Agentic Framework that Uses Computers Like a Human", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/394c7c30ea87b5c3521b4d9e9d419071-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2410_08164, title = {{Agent S: An Open Agentic Framework that Uses Computers Like a Human}}, author = {{Saaket Agashe} and {Jiuzhou Han} and {Shuyu Gan} and {Jiachen Yang} and {Ang Li} and {Xin Eric Wang}}, year = {2024}, eprint = {2410.08164v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.08164v1}, note = {First published: 2024-10-10; Recorded arXiv version: v1; Recorded version updated: 2024-10-10T17:43:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.09006", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.09006"}} @misc{arxiv_2410_09006, title = {{From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts}}, author = {{Zhuohao Jerry Zhang} and {Eldon Schoop} and {Jeffrey Nichols} and {Anuj Mahajan} and {Amanda Swearngin}}, year = {2024}, eprint = {2410.09006v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.09006v2}, note = {First published: 2024-10-11; Recorded arXiv version: v2; Recorded version updated: 2025-03-22T18:01:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.11871", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.11871"}} @misc{arxiv_2410_11871, title = {{TinyClick: Single-Turn Agent for Empowering GUI Automation}}, author = {{Pawel Pawlowski} and {Krystian Zawistowski} and {Wojciech Lapacz} and {Adam Wiacek} and {Marcin Skorupa} and {Sebastien Postansque} and {Jakub Hoscilowicz}}, year = {2024}, eprint = {2410.11871v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.11871v3}, note = {First published: 2024-10-09; Recorded arXiv version: v3; Recorded version updated: 2025-05-21T06:52:31Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.11872", "catalog_id": "arxiv:2410.11872", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.11872"}, "publication": {"authors": ["Jakub Hoscilowicz", "Bartosz Maj", "Bartosz Kozakiewicz", "Oleksii Tymoshchuk", "Artur Janicki"], "date_basis": "Explicit publisher citation_publication_date: 2025/8. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 8], "doi": "10.18653/v1/2025.sigdial-1.38", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.sigdial-1.38/", "https://aclanthology.org/2025.sigdial-1.38.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the five-author list on page 1 of the publisher PDF. Landing-page citation metadata lists only Jakub Hoscilowicz and Artur Janicki.", "pages": "471-476", "pdf_url": "https://aclanthology.org/2025.sigdial-1.38.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.sigdial-1.38/", "venue": "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue", "volume": null}} @misc{arxiv_2410_11872, title = {{ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents}}, author = {{Jakub Hoscilowicz} and {Bartosz Maj} and {Bartosz Kozakiewicz} and {Oleksii Tymoshchuk} and {Artur Janicki}}, year = {2024}, eprint = {2410.11872v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.11872v2}, note = {First published: 2024-10-09; Recorded arXiv version: v2; Recorded version updated: 2024-10-17T07:12:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.13232", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.13232"}} @misc{arxiv_2410_13232, title = {{Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation}}, author = {{Hyungjoo Chae} and {Namyoung Kim} and {Kai Tzu-iunn Ong} and {Minju Gwak} and {Gwanwoo Song} and {Jihoon Kim} and {Sunghwan Kim} and {Dongha Lee} and {Jinyoung Yeo}}, year = {2024}, eprint = {2410.13232v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13232v2}, note = {First published: 2024-10-17; Recorded arXiv version: v2; Recorded version updated: 2025-03-29T08:59:09Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.13757", "catalog_id": "arxiv:2410.13757", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.13757"}, "publication": {"authors": ["Zichen Zhu", "Hao Tang", "Yansi Li", "Dingye Liu", "Hongshen Xu", "Kunyao Lan", "Danyang Zhang", "Yixuan Jiang", "Hao Zhou", "Chenrun Wang", "Situo Zhang", "Liangtai Sun", "Yixiao Wang", "Yuheng Sun", "Lu Chen", "Kai Yu"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-demo.43", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-demo.43/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "535-549", "pdf_url": "https://aclanthology.org/2025.naacl-demo.43.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.43/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null}} @misc{arxiv_2410_13757, title = {{MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation}}, author = {{Zichen Zhu} and {Hao Tang} and {Yansi Li} and {Dingye Liu} and {Hongshen Xu} and {Kunyao Lan} and {Danyang Zhang} and {Yixuan Jiang} and {Hao Zhou} and {Chenrun Wang} and {Situo Zhang} and {Liangtai Sun} and {Yixiao Wang} and {Yuheng Sun} and {Lu Chen} and {Kai Yu}}, year = {2024}, eprint = {2410.13757v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13757v3}, note = {First published: 2024-10-17; Recorded arXiv version: v3; Recorded version updated: 2025-05-13T06:25:09Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.13824", "catalog_id": "arxiv:2410.13824", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.13824"}, "publication": {"authors": ["Junpeng Liu", "Tianyue Ou", "Yifan Song", "Yuxiao Qu", "Wai Lam", "Chenyan Xiong", "Wenhu Chen", "Graham Neubig", "Xiang Yue"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "17971-18005", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/2da53cd1abdae59150e35f4693834f32-Paper-Conference.pdf", "publisher": null, "series": null, "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2410_13824, title = {{Harnessing Webpage UIs for Text-Rich Visual Understanding}}, author = {{Junpeng Liu} and {Tianyue Ou} and {Yifan Song} and {Yuxiao Qu} and {Wai Lam} and {Chenyan Xiong} and {Wenhu Chen} and {Graham Neubig} and {Xiang Yue}}, year = {2024}, eprint = {2410.13824v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13824v3}, note = {First published: 2024-10-17; Recorded arXiv version: v3; Recorded version updated: 2024-11-06T08:29:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.13825", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.13825"}} @misc{arxiv_2410_13825, title = {{AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents}}, author = {{Ke Yang} and {Yao Liu} and {Sapana Chaudhary} and {Rasool Fakoor} and {Pratik Chaudhari} and {George Karypis} and {Huzefa Rangwala}}, year = {2024}, eprint = {2410.13825v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13825v2}, note = {First published: 2024-10-17; Recorded arXiv version: v2; Recorded version updated: 2025-05-24T03:55:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.13886", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.13886"}} @misc{arxiv_2410_13886, title = {{Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents}}, author = {{Priyanshu Kumar} and {Elaine Lau} and {Saranya Vijayakumar} and {Tu Trinh} and {Scale Red Team} and {Elaine Chang} and {Vaughn Robinson} and {Sean Hendryx} and {Shuyan Zhou} and {Matt Fredrikson} and {Summer Yue} and {Zifan Wang}}, year = {2024}, eprint = {2410.13886v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13886v2}, note = {First published: 2024-10-11; Recorded arXiv version: v2; Recorded version updated: 2024-10-21T18:06:58Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.14803", "catalog_id": "arxiv:2410.14803", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.14803"}, "publication": {"authors": ["Taiyi Wang", "Zhihao Wu", "Jianheng Liu", "Jianye HAO", "Jun Wang", "Kun Shao"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/b9e472cd579c83e2f6aa3459f46aac28-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher title uses singular Agent; the preprint uses Agents. The authors and DistRL contribution agree.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "74757-74782", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/b9e472cd579c83e2f6aa3459f46aac28-Paper-Conference.pdf", "publisher": null, "series": null, "title": "DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/b9e472cd579c83e2f6aa3459f46aac28-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2410_14803, title = {{DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents}}, author = {{Taiyi Wang} and {Zhihao Wu} and {Jianheng Liu} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2024}, eprint = {2410.14803v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.14803v5}, note = {First published: 2024-10-18; Recorded arXiv version: v5; Recorded version updated: 2025-02-21T16:23:59Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.15164", "catalog_id": "arxiv:2410.15164", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.15164"}, "publication": {"authors": ["Jingxuan Chen", "Derek Yuen", "Bin Xie", "Yuhao Yang", "Gongwei Chen", "Zhihao Wu", "Li Yixing", "Xurui Zhou", "Weiwen Liu", "Shuai Wang", "Kaiwen Zhou", "Rui Shao", "Liqiang Nie", "Yasheng Wang", "Jianye HAO", "Jun Wang", "Kun Shao"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "61769-61806", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/9a75f4dd9679aa4ff80a4e6f0a1dc700-Paper-Conference.pdf", "publisher": null, "series": null, "title": "SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/9a75f4dd9679aa4ff80a4e6f0a1dc700-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2410_15164, title = {{SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation}}, author = {{Jingxuan Chen} and {Derek Yuen} and {Bin Xie} and {Yuhao Yang} and {Gongwei Chen} and {Zhihao Wu} and {Li Yixing} and {Xurui Zhou} and {Weiwen Liu} and {Shuai Wang} and {Kaiwen Zhou} and {Rui Shao} and {Liqiang Nie} and {Yasheng Wang} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2024}, eprint = {2410.15164v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.15164v3}, note = {First published: 2024-10-19; Recorded arXiv version: v3; Recorded version updated: 2025-03-31T20:39:17Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.16464", "catalog_id": "arxiv:2410.16464", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.16464"}, "publication": {"authors": ["Yueqi Song", "Frank F. Xu", "Shuyan Zhou", "Graham Neubig"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.577", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.577/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "11066-11085", "pdf_url": "https://aclanthology.org/2025.findings-acl.577.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Beyond Browsing: API-Based Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.577/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2410_16464, title = {{Beyond Browsing: API-Based Web Agents}}, author = {{Yueqi Song} and {Frank Xu} and {Shuyan Zhou} and {Graham Neubig}}, year = {2024}, eprint = {2410.16464v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.16464v3}, note = {First published: 2024-10-21; Recorded arXiv version: v3; Recorded version updated: 2025-06-16T22:23:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.17401", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.17401"}} @misc{arxiv_2410_17401, title = {{AdvAgent: Controllable Blackbox Red-teaming on Web Agents}}, author = {{Chejian Xu} and {Mintong Kang} and {Jiawei Zhang} and {Zeyi Liao} and {Lingbo Mo} and {Mengqi Yuan} and {Huan Sun} and {Bo Li}}, year = {2024}, eprint = {2410.17401v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.17401v4}, note = {First published: 2024-10-22; Recorded arXiv version: v4; Recorded version updated: 2025-05-31T18:34:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.17520", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.17520"}} @misc{arxiv_2410_17520, title = {{MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control}}, author = {{Juyong Lee} and {Dongyoon Hahm} and {June Suk Choi} and {W. Bradley Knox} and {Kimin Lee}}, year = {2024}, eprint = {2410.17520v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.17520v3}, note = {First published: 2024-10-23; Recorded arXiv version: v3; Recorded version updated: 2026-01-27T01:51:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.17883", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.17883"}} @misc{arxiv_2410_17883, title = {{Lightweight Neural App Control}}, author = {{Filippos Christianos} and {Georgios Papoudakis} and {Thomas Coste} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2024}, eprint = {2410.17883v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.17883v2}, note = {First published: 2024-10-23; Recorded arXiv version: v2; Recorded version updated: 2025-02-12T17:51:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.18603", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.18603"}} @misc{arxiv_2410_18603, title = {{AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant}}, author = {{Chengyou Jia} and {Minnan Luo} and {Zhuohang Dang} and {Qiushi Sun} and {Fangzhi Xu} and {Junlin Hu} and {Tianbao Xie} and {Zhiyong Wu}}, year = {2024}, eprint = {2410.18603v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.18603v1}, note = {First published: 2024-10-24; Recorded arXiv version: v1; Recorded version updated: 2024-10-24T09:58:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.18963", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.18963"}} @misc{arxiv_2410_18963, title = {{OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning}}, author = {{Xiaoqiang Wang} and {Bang Liu}}, year = {2024}, eprint = {2410.18963v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.18963v1}, note = {First published: 2024-10-24; Recorded arXiv version: v1; Recorded version updated: 2024-10-24T17:58:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.18967", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.18967"}} @misc{arxiv_2410_18967, title = {{Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms}}, author = {{Zhangheng Li} and {Keen You} and {Haotian Zhang} and {Di Feng} and {Harsh Agrawal} and {Xiujun Li} and {Mohana Prasad Sathya Moorthy} and {Jeff Nichols} and {Yinfei Yang} and {Zhe Gan}}, year = {2024}, eprint = {2410.18967v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.18967v2}, note = {First published: 2024-10-24; Recorded arXiv version: v2; Recorded version updated: 2025-02-28T00:29:14Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.19100", "catalog_id": "arxiv:2410.19100", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.19100"}, "publication": {"authors": ["Lawrence Jang", "Yinheng Li", "Dan Zhao", "Charles Ding", "Justin Lin", "Paul Pu Liang", "Rogerio Bonatti", "Kazuhito Koishida"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "36934-36958", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/5b555804d495321df2e3208cc27f4fbc-Paper-Conference.pdf", "publisher": null, "series": null, "title": "VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}} @misc{arxiv_2410_19100, title = {{VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks}}, author = {{Lawrence Jang} and {Yinheng Li} and {Dan Zhao} and {Charles Ding} and {Justin Lin} and {Paul Pu Liang} and {Rogerio Bonatti} and {Kazuhito Koishida}}, year = {2024}, eprint = {2410.19100v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.19100v3}, note = {First published: 2024-10-24; Recorded arXiv version: v3; Recorded version updated: 2025-02-15T05:19:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.19461", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.19461"}} @misc{arxiv_2410_19461, title = {{EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data}}, author = {{Xuetian Chen} and {Hangcheng Li} and {Jiaqing Liang} and {Sihang Jiang} and {Deqing Yang}}, year = {2024}, eprint = {2410.19461v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.19461v2}, note = {First published: 2024-10-25; Recorded arXiv version: v2; Recorded version updated: 2024-11-02T08:54:21Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.19609", "catalog_id": "arxiv:2410.19609", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.19609"}, "publication": {"authors": ["Hongliang He", "Wenlin Yao", "Kaixin Ma", "Wenhao Yu", "Hongming Zhang", "Tianqing Fang", "Zhenzhong Lan", "Dong Yu"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.1336", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.1336/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "27545-27564", "pdf_url": "https://aclanthology.org/2025.acl-long.1336.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.1336/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2410_19609, title = {{OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization}}, author = {{Hongliang He} and {Wenlin Yao} and {Kaixin Ma} and {Wenhao Yu} and {Hongming Zhang} and {Tianqing Fang} and {Zhenzhong Lan} and {Dong Yu}}, year = {2024}, eprint = {2410.19609v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.19609v1}, note = {First published: 2024-10-25; Recorded arXiv version: v1; Recorded version updated: 2024-10-25T15:01:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.22552", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.22552"}} @misc{arxiv_2410_22552, title = {{Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents}}, author = {{Jaekyeom Kim} and {Dong-Ki Kim} and {Lajanugen Logeswaran} and {Sungryull Sohn} and {Honglak Lee}}, year = {2024}, eprint = {2410.22552v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.22552v1}, note = {First published: 2024-10-29; Recorded arXiv version: v1; Recorded version updated: 2024-10-29T21:37:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.23218", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.23218"}} @misc{arxiv_2410_23218, title = {{OS-ATLAS: A Foundation Action Model for Generalist GUI Agents}}, author = {{Zhiyong Wu} and {Zhenyu Wu} and {Fangzhi Xu} and {Yian Wang} and {Qiushi Sun} and {Chengyou Jia} and {Kanzhi Cheng} and {Zichen Ding} and {Liheng Chen} and {Paul Pu Liang} and {Yu Qiao}}, year = {2024}, eprint = {2410.23218v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.23218v1}, note = {First published: 2024-10-30; Recorded arXiv version: v1; Recorded version updated: 2024-10-30T17:10:19Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.23252", "catalog_id": "arxiv:2410.23252", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.23252"}, "publication": {"authors": ["Haoyi Qiu", "Alexander Richard Fabbri", "Divyansh Agarwal", "Kung-Hsiang Huang", "Sarah Tan", "Nanyun Peng", "Chien-Sheng Wu"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.findings-naacl.222", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-naacl.222/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "3978-4005", "pdf_url": "https://aclanthology.org/2025.findings-naacl.222.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Evaluating Cultural and Social Awareness of LLM Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-naacl.222/", "venue": "Findings of the Association for Computational Linguistics: NAACL 2025", "volume": null}} @misc{arxiv_2410_23252, title = {{Evaluating Cultural and Social Awareness of LLM Web Agents}}, author = {{Haoyi Qiu} and {Alexander R. Fabbri} and {Divyansh Agarwal} and {Kung-Hsiang Huang} and {Sarah Tan} and {Nanyun Peng} and {Chien-Sheng Wu}}, year = {2024}, eprint = {2410.23252v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.23252v3}, note = {First published: 2024-10-30; Recorded arXiv version: v3; Recorded version updated: 2025-03-08T23:37:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2410.23555", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2410.23555"}} @misc{arxiv_2410_23555, title = {{From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents}}, author = {{Nalin Tiwary} and {Vardhan Dongre} and {Sanil Arun Chawla} and {Ashwin Lamani} and {Dilek Hakkani-Tür}}, year = {2024}, eprint = {2410.23555v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.23555v1}, note = {First published: 2024-10-31; Recorded arXiv version: v1; Recorded version updated: 2024-10-31T01:51:41Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.24024", "catalog_id": "arxiv:2410.24024", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.24024"}, "publication": {"authors": ["Yifan Xu", "Xiao Liu", "Xueqiao Sun", "Siyi Cheng", "Hao Yu (\u4f59\u6d69)", "Hanyu Lai", "Shudan Zhang", "Dan Zhang", "Jie Tang", "Yuxiao Dong"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.107", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.107/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "2144-2166", "pdf_url": "https://aclanthology.org/2025.acl-long.107.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.107/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2410_24024, title = {{AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents}}, author = {{Yifan Xu} and {Xiao Liu} and {Xueqiao Sun} and {Siyi Cheng} and {Hao Yu} and {Hanyu Lai} and {Shudan Zhang} and {Dan Zhang} and {Jie Tang} and {Yuxiao Dong}}, year = {2024}, eprint = {2410.24024v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.24024v2}, note = {First published: 2024-10-31; Recorded arXiv version: v2; Recorded version updated: 2024-11-04T05:57:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.00820", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.00820"}} @misc{arxiv_2411_00820, title = {{AutoGLM: Autonomous Foundation Agents for GUIs}}, author = {{Xiao Liu} and {Bo Qin} and {Dongzhu Liang} and {Guang Dong} and {Hanyu Lai} and {Hanchen Zhang} and {Hanlin Zhao} and {Iat Long Iong} and {Jiadai Sun} and {Jiaqi Wang} and {Junjie Gao} and {Junjun Shan} and {Kangning Liu} and {Shudan Zhang} and {Shuntian Yao} and {Siyi Cheng} and {Wentao Yao} and {Wenyi Zhao} and {Xinghan Liu} and {Xinyi Liu} and {Xinying Chen} and {Xinyue Yang} and {Yang Yang} and {Yifan Xu} and {Yu Yang} and {Yujia Wang} and {Yulin Xu} and {Zehan Qi} and {Yuxiao Dong} and {Jie Tang}}, year = {2024}, eprint = {2411.00820v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.00820v1}, note = {First published: 2024-10-28; Recorded arXiv version: v1; Recorded version updated: 2024-10-28T17:05:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.02006", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.02006"}} @misc{arxiv_2411_02006, title = {{Foundations and Recent Trends in Multimodal Mobile Agents: A Survey}}, author = {{Biao Wu} and {Yanda Li} and {Zhiwei Zhang} and {Yunchao Wei} and {Meng Fang} and {Ling Chen}}, year = {2024}, eprint = {2411.02006v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.02006v3}, note = {First published: 2024-11-04; Recorded arXiv version: v3; Recorded version updated: 2025-09-14T09:13:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.02337", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.02337"}} @misc{arxiv_2411_02337, title = {{WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning}}, author = {{Zehan Qi} and {Xiao Liu} and {Iat Long Iong} and {Hanyu Lai} and {Xueqiao Sun} and {Wenyi Zhao} and {Yu Yang} and {Xinyue Yang} and {Jiadai Sun} and {Shuntian Yao} and {Tianjie Zhang} and {Wei Xu} and {Jie Tang} and {Yuxiao Dong}}, year = {2024}, eprint = {2411.02337v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.02337v3}, note = {First published: 2024-11-04; Recorded arXiv version: v3; Recorded version updated: 2025-01-27T11:56:15Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2411.02391", "catalog_id": "arxiv:2411.02391", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2411.02391"}, "publication": {"authors": ["Yanzhe Zhang", "Tao Yu", "Diyi Yang"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.411", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.411/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "8387-8401", "pdf_url": "https://aclanthology.org/2025.acl-long.411.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Attacking Vision-Language Computer Agents via Pop-ups", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.411/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2411_02391, title = {{Attacking Vision-Language Computer Agents via Pop-ups}}, author = {{Yanzhe Zhang} and {Tao Yu} and {Diyi Yang}}, year = {2024}, eprint = {2411.02391v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.02391v2}, note = {First published: 2024-11-04; Recorded arXiv version: v2; Recorded version updated: 2025-05-24T16:15:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.03817", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2411.03817"}} @misc{arxiv_2411_03817, title = {{From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning}}, author = {{Zhirui Deng} and {Zhicheng Dou} and {Yutao Zhu} and {Ji-Rong Wen} and {Ruibin Xiong} and {Mang Wang} and {Weipeng Chen}}, year = {2024}, eprint = {2411.03817v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.03817v3}, note = {First published: 2024-11-06; Recorded arXiv version: v3; Recorded version updated: 2024-12-09T09:20:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.04468", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2411.04468"}} @misc{arxiv_2411_04468, title = {{Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks}}, author = {{Adam Fourney} and {Gagan Bansal} and {Hussein Mozannar} and {Cheng Tan} and {Eduardo Salinas} and {Erkang} and {Zhu} and {Friederike Niedtner} and {Grace Proebsting} and {Griffin Bassman} and {Jack Gerrits} and {Jacob Alber} and {Peter Chang} and {Ricky Loynd} and {Robert West} and {Victor Dibia} and {Ahmed Awadallah} and {Ece Kamar} and {Rafah Hosn} and {Saleema Amershi}}, year = {2024}, eprint = {2411.04468v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.04468v1}, note = {First published: 2024-11-07; Recorded arXiv version: v1; Recorded version updated: 2024-11-07T06:36:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.04890", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.04890"}} @misc{arxiv_2411_04890, title = {{GUI Agents with Foundation Models: A Comprehensive Survey}}, author = {{Shuai Wang} and {Weiwen Liu} and {Jingxuan Chen} and {Yuqi Zhou} and {Weinan Gan} and {Xingshan Zeng} and {Yuhan Che} and {Shuai Yu} and {Xinlong Hao} and {Kun Shao} and {Bin Wang} and {Chuhan Wu} and {Yasheng Wang} and {Ruiming Tang} and {Jianye Hao}}, year = {2024}, eprint = {2411.04890v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.04890v2}, note = {First published: 2024-11-07; Recorded arXiv version: v2; Recorded version updated: 2025-02-13T10:09:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.06559", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.06559"}} @misc{arxiv_2411_06559, title = {{Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents}}, author = {{Yu Gu} and {Kai Zhang} and {Yuting Ning} and {Boyuan Zheng} and {Boyu Gou} and {Tianci Xue} and {Cheng Chang} and {Sanjari Srivastava} and {Yanan Xie} and {Peng Qi} and {Huan Sun} and {Yu Su}}, year = {2024}, eprint = {2411.06559v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.06559v2}, note = {First published: 2024-11-10; Recorded arXiv version: v2; Recorded version updated: 2025-04-01T05:04:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.10323", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.10323"}} @misc{arxiv_2411_10323, title = {{The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use}}, author = {{Siyuan Hu} and {Mingyu Ouyang} and {Difei Gao} and {Mike Zheng Shou}}, year = {2024}, eprint = {2411.10323v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.10323v1}, note = {First published: 2024-11-15; Recorded arXiv version: v1; Recorded version updated: 2024-11-15T16:23:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.10943", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.10943"}} @misc{arxiv_2411_10943, title = {{Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms}}, author = {{Minghe Gao} and {Wendong Bu} and {Bingchen Miao} and {Yang Wu} and {Yunfei Li} and {Juncheng Li} and {Siliang Tang} and {Qi Wu} and {Yueting Zhuang} and {Meng Wang}}, year = {2024}, eprint = {2411.10943v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.10943v1}, note = {First published: 2024-11-17; Recorded arXiv version: v1; Recorded version updated: 2024-11-17T02:44:56Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2411.13451", "catalog_id": "arxiv:2411.13451", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2411.13451"}, "publication": {"authors": ["Gaurav Verma", "Rachneet Kaur", "Nishan Srishankar", "Zhen Zeng", "Tucker Balch", "Manuela Veloso"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.1008", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.1008/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "20635-20651", "pdf_url": "https://aclanthology.org/2025.acl-long.1008.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.1008/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2411_13451, title = {{AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations}}, author = {{Gaurav Verma} and {Rachneet Kaur} and {Nishan Srishankar} and {Zhen Zeng} and {Tucker Balch} and {Manuela Veloso}}, year = {2024}, eprint = {2411.13451v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.13451v1}, note = {First published: 2024-11-20; Recorded arXiv version: v1; Recorded version updated: 2024-11-20T16:54:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.13591", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.13591"}} @misc{arxiv_2411_13591, title = {{Improved GUI Grounding via Iterative Narrowing}}, author = {{Anthony Nguyen}}, year = {2024}, eprint = {2411.13591v7}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.13591v7}, note = {First published: 2024-11-18; Recorded arXiv version: v7; Recorded version updated: 2025-09-11T16:37:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.15004", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.15004"}} @misc{arxiv_2411_15004, title = {{ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data}}, author = {{Junhong Shen} and {Atishay Jain} and {Zedian Xiao} and {Ishan Amlekar} and {Mouad Hadji} and {Aaron Podolny} and {Ameet Talwalkar}}, year = {2024}, eprint = {2411.15004v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.15004v2}, note = {First published: 2024-11-22; Recorded arXiv version: v2; Recorded version updated: 2024-12-05T02:00:07Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2411.17465", "catalog_id": "arxiv:2411.17465", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2411.17465"}, "publication": {"authors": ["Kevin Qinghong Lin", "Linjie Li", "Difei Gao", "Zhengyuan Yang", "Shiwei Wu", "Zechen Bai", "Stan Weixian Lei", "Lijuan Wang", "Mike Zheng Shou"], "date_basis": "Year from publisher citation metadata and month from the same page's embedded BibTeX; no day is supplied.", "date_parts": [2025, 6], "doi": null, "event_dates": null, "evidence_urls": ["https://openaccess.thecvf.com/content/CVPR2025/html/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher page directly links this arXiv identifier.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "19498-19508", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2025/papers/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.pdf", "publisher": null, "series": null, "title": "ShowUI: One Vision-Language-Action Model for GUI Visual Agent", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition", "volume": null}} @misc{arxiv_2411_17465, title = {{ShowUI: One Vision-Language-Action Model for GUI Visual Agent}}, author = {{Kevin Qinghong Lin} and {Linjie Li} and {Difei Gao} and {Zhengyuan Yang} and {Shiwei Wu} and {Zechen Bai} and {Weixian Lei} and {Lijuan Wang} and {Mike Zheng Shou}}, year = {2024}, eprint = {2411.17465v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.17465v1}, note = {First published: 2024-11-26; Recorded arXiv version: v1; Recorded version updated: 2024-11-26T14:29:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2411.18279", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2411.18279"}} @misc{arxiv_2411_18279, title = {{Large Language Model-Brained GUI Agents: A Survey}}, author = {{Chaoyun Zhang} and {Shilin He} and {Jiaxu Qian} and {Bowen Li} and {Liqun Li} and {Si Qin} and {Yu Kang} and {Minghua Ma} and {Guyue Liu} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang} and {Qi Zhang}}, year = {2024}, eprint = {2411.18279v12}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.18279v12}, note = {First published: 2024-11-27; Recorded arXiv version: v12; Recorded version updated: 2025-05-06T15:08:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.00402", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2412.00402"}} @misc{arxiv_2412_00402, title = {{DroidCall: A Dataset for LLM-powered Android Intent Invocation}}, author = {{Weikai Xie} and {Li Zhang} and {Shihe Wang} and {Rongjie Yi} and {Mengwei Xu}}, year = {2024}, eprint = {2412.00402v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.00402v1}, note = {First published: 2024-11-30; Recorded arXiv version: v1; Recorded version updated: 2024-11-30T08:55:39Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2412.01268", "catalog_id": "arxiv:2412.01268", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2412.01268"}, "publication": {"authors": ["Yiqin Wang", "Haoji Zhang", "Jingqi Tian", "Yansong Tang"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.76", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.76/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "1461-1473", "pdf_url": "https://aclanthology.org/2025.findings-acl.76.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Ponder & Press: Advancing Visual GUI Agent towards General Computer Control", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.76/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2412_01268, title = {{Ponder \& Press: Advancing Visual GUI Agent towards General Computer Control}}, author = {{Yiqin Wang} and {Haoji Zhang} and {Jingqi Tian} and {Yansong Tang}}, year = {2024}, eprint = {2412.01268v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.01268v1}, note = {First published: 2024-12-02; Recorded arXiv version: v1; Recorded version updated: 2024-12-02T08:35:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.04454", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.04454"}} @misc{arxiv_2412_04454, title = {{Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction}}, author = {{Yiheng Xu} and {Zekun Wang} and {Junli Wang} and {Dunjie Lu} and {Tianbao Xie} and {Amrita Saha} and {Doyen Sahoo} and {Tao Yu} and {Caiming Xiong}}, year = {2024}, eprint = {2412.04454v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.04454v2}, note = {First published: 2024-12-05; Recorded arXiv version: v2; Recorded version updated: 2025-05-05T16:17:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.05467", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.05467"}} @misc{arxiv_2412_05467, title = {{The BrowserGym Ecosystem for Web Agent Research}}, author = {{Thibault Le Sellier De Chezelles} and {Maxime Gasse} and {Alexandre Drouin} and {Massimo Caccia} and {Léo Boisvert} and {Megh Thakkar} and {Tom Marty} and {Rim Assouel} and {Sahar Omidi Shayegan} and {Lawrence Keunho Jang} and {Xing Han Lù} and {Ori Yoran} and {Dehan Kong} and {Frank F. Xu} and {Siva Reddy} and {Quentin Cappart} and {Graham Neubig} and {Ruslan Salakhutdinov} and {Nicolas Chapados} and {Alexandre Lacoste}}, year = {2024}, eprint = {2412.05467v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.05467v4}, note = {First published: 2024-12-06; Recorded arXiv version: v4; Recorded version updated: 2025-02-28T16:02:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.09362", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.09362"}} @misc{arxiv_2412_09362, title = {{Falcon-UI: Understanding GUI Before Following User Instructions}}, author = {{Huawen Shen} and {Chang Liu} and {Gengluo Li} and {Xinlong Wang} and {Yu Zhou} and {Can Ma} and {Xiangyang Ji}}, year = {2024}, eprint = {2412.09362v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.09362v1}, note = {First published: 2024-12-12; Recorded arXiv version: v1; Recorded version updated: 2024-12-12T15:29:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.09605", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.09605"}} @misc{arxiv_2412_09605, title = {{AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials}}, author = {{Yiheng Xu} and {Dunjie Lu} and {Zhennan Shen} and {Junli Wang} and {Zekun Wang} and {Yuchen Mao} and {Caiming Xiong} and {Tao Yu}}, year = {2024}, eprint = {2412.09605v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.09605v2}, note = {First published: 2024-12-12; Recorded arXiv version: v2; Recorded version updated: 2025-03-03T18:59:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.10047", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.10047"}} @misc{arxiv_2412_10047, title = {{Large Action Models: From Inception to Implementation}}, author = {{Lu Wang} and {Fangkai Yang} and {Chaoyun Zhang} and {Junting Lu} and {Jiaxu Qian} and {Shilin He} and {Pu Zhao} and {Bo Qiao} and {Ray Huang} and {Si Qin} and {Qisheng Su} and {Jiayi Ye} and {Yudi Zhang} and {Jian-Guang Lou} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang} and {Qi Zhang}}, year = {2024}, eprint = {2412.10047v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10047v2}, note = {First published: 2024-12-13; Recorded arXiv version: v2; Recorded version updated: 2025-01-13T06:47:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.10342", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.10342"}} @misc{arxiv_2412_10342, title = {{Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining}}, author = {{Zhiqi Ge} and {Juncheng Li} and {Xinglei Pang} and {Minghe Gao} and {Kaihang Pan} and {Wang Lin} and {Hao Fei} and {Wenqiao Zhang} and {Siliang Tang} and {Yueting Zhuang}}, year = {2024}, eprint = {2412.10342v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10342v2}, note = {First published: 2024-12-13; Recorded arXiv version: v2; Recorded version updated: 2025-02-03T15:23:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.10742", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.10742"}} @misc{arxiv_2412_10742, title = {{WEPO: Web Element Preference Optimization for LLM-based Web Navigation}}, author = {{Jiarun Liu} and {Jia Hao} and {Chunhong Zhang} and {Zheng Hu}}, year = {2024}, eprint = {2412.10742v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10742v1}, note = {First published: 2024-12-14; Recorded arXiv version: v1; Recorded version updated: 2024-12-14T08:25:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.10840", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.10840"}} @misc{arxiv_2412_10840, title = {{Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning}}, author = {{Hai-Ming Xu} and {Qi Chen} and {Lei Wang} and {Lingqiao Liu}}, year = {2024}, eprint = {2412.10840v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10840v1}, note = {First published: 2024-12-14; Recorded arXiv version: v1; Recorded version updated: 2024-12-14T14:30:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.13194", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.13194"}} @misc{arxiv_2412_13194, title = {{Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents}}, author = {{Yifei Zhou} and {Qianlan Yang} and {Kaixiang Lin} and {Min Bai} and {Xiong Zhou} and {Yu-Xiong Wang} and {Sergey Levine} and {Erran Li}}, year = {2024}, eprint = {2412.13194v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.13194v1}, note = {First published: 2024-12-17; Recorded arXiv version: v1; Recorded version updated: 2024-12-17T18:59:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.13501", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.13501"}} @misc{arxiv_2412_13501, title = {{GUI Agents: A Survey}}, author = {{Dang Nguyen} and {Jian Chen} and {Yu Wang} and {Gang Wu} and {Namyong Park} and {Zhengmian Hu} and {Hanjia Lyu} and {Junda Wu} and {Ryan Aponte} and {Yu Xia} and {Xintong Li} and {Jing Shi} and {Hongjie Chen} and {Viet Dac Lai} and {Zhouhang Xie} and {Sungchul Kim} and {Ruiyi Zhang} and {Tong Yu} and {Mehrab Tanjim} and {Nesreen K. Ahmed} and {Puneet Mathur} and {Seunghyun Yoon} and {Lina Yao} and {Branislav Kveton} and {Jihyung Kil} and {Thien Huu Nguyen} and {Trung Bui} and {Tianyi Zhou} and {Ryan A. Rossi} and {Franck Dernoncourt}}, year = {2024}, eprint = {2412.13501v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.13501v3}, note = {First published: 2024-12-18; Recorded arXiv version: v3; Recorded version updated: 2025-09-26T21:01:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.14161", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.14161"}} @misc{arxiv_2412_14161, title = {{TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks}}, author = {{Frank F. Xu} and {Yufan Song} and {Boxuan Li} and {Yuxuan Tang} and {Kritanjali Jain} and {Mengxue Bao} and {Zora Z. Wang} and {Xuhui Zhou} and {Zhitong Guo} and {Murong Cao} and {Mingyang Yang} and {Hao Yang Lu} and {Amaad Martin} and {Zhe Su} and {Leander Maben} and {Raj Mehta} and {Wayne Chi} and {Lawrence Jang} and {Yiqing Xie} and {Shuyan Zhou} and {Graham Neubig}}, year = {2024}, eprint = {2412.14161v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.14161v3}, note = {First published: 2024-12-18; Recorded arXiv version: v3; Recorded version updated: 2025-09-10T08:35:19Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2412.16256", "catalog_id": "arxiv:2412.16256", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2412.16256"}, "publication": {"authors": ["Yuhao Yang", "Yue Wang", "Dongxu Li", "Ziyang Luo", "Bei Chen", "Chao Huang", "Junnan Li"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.1152", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.1152/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "22418-22433", "pdf_url": "https://aclanthology.org/2025.findings-acl.1152.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Aria-UI: Visual Grounding for GUI Instructions", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.1152/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2412_16256, title = {{Aria-UI: Visual Grounding for GUI Instructions}}, author = {{Yuhao Yang} and {Yue Wang} and {Dongxu Li} and {Ziyang Luo} and {Bei Chen} and {Chao Huang} and {Junnan Li}}, year = {2024}, eprint = {2412.16256v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.16256v2}, note = {First published: 2024-12-20; Recorded arXiv version: v2; Recorded version updated: 2025-07-08T08:49:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.17589", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.17589"}} @misc{arxiv_2412_17589, title = {{PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World}}, author = {{Yanheng He} and {Jiahe Jin} and {Shijie Xia} and {Jiadi Su} and {Runze Fan} and {Haoyang Zou} and {Xiangkun Hu} and {Pengfei Liu}}, year = {2024}, eprint = {2412.17589v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.17589v1}, note = {First published: 2024-12-23; Recorded arXiv version: v1; Recorded version updated: 2024-12-23T14:02:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.18116", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.18116"}} @misc{arxiv_2412_18116, title = {{AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation}}, author = {{Hao Wen} and {Shizuo Tian} and {Borislav Pavlov} and {Wenjie Du} and {Yixuan Li} and {Ge Chang} and {Shanhui Zhao} and {Jiacheng Liu} and {Yunxin Liu} and {Ya-Qin Zhang} and {Yuanchun Li}}, year = {2024}, eprint = {2412.18116v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.18116v3}, note = {First published: 2024-12-24; Recorded arXiv version: v3; Recorded version updated: 2025-05-06T12:24:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2412.18426", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2412.18426"}} @misc{arxiv_2412_18426, title = {{GUI Testing Arena: A Unified Benchmark for Advancing Autonomous GUI Testing Agent}}, author = {{Kangjia Zhao} and {Jiahui Song} and {Leigang Sha} and {Haozhan Shen} and {Zhi Chen} and {Tiancheng Zhao} and {Xiubo Liang} and {Jianwei Yin}}, year = {2024}, eprint = {2412.18426v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.18426v1}, note = {First published: 2024-12-24; Recorded arXiv version: v1; Recorded version updated: 2024-12-24T13:41:47Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2412.19723", "catalog_id": "arxiv:2412.19723", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2412.19723"}, "publication": {"authors": ["Qiushi Sun", "Kanzhi Cheng", "Zichen Ding", "Chuanyang Jin", "Yian Wang", "Fangzhi Xu", "Zhenyu Wu", "Chengyou Jia", "Liheng Chen", "Zhoumianze Liu", "Ben Kao", "Guohao Li", "Junxian He", "Yu Qiao", "Zhiyong Wu"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.277", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.277/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "5555-5579", "pdf_url": "https://aclanthology.org/2025.acl-long.277.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.277/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2412_19723, title = {{OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis}}, author = {{Qiushi Sun} and {Kanzhi Cheng} and {Zichen Ding} and {Chuanyang Jin} and {Yian Wang} and {Fangzhi Xu} and {Zhenyu Wu} and {Chengyou Jia} and {Liheng Chen} and {Zhoumianze Liu} and {Ben Kao} and {Guohao Li} and {Junxian He} and {Yu Qiao} and {Zhiyong Wu}}, year = {2024}, eprint = {2412.19723v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.19723v3}, note = {First published: 2024-12-27; Recorded arXiv version: v3; Recorded version updated: 2025-06-27T08:25:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.01149", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.01149"}} @misc{arxiv_2501_01149, title = {{A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation}}, author = {{Yuxiang Chai} and {Shunye Tang} and {Han Xiao} and {Weifeng Lin} and {Hanhao Li} and {Jiayu Zhang} and {Liang Liu} and {Pengxiang Zhao} and {Guangyi Liu} and {Guozhi Wang} and {Shuai Ren} and {Rongduo Han} and {Haining Zhang} and {Siyuan Huang} and {Hongsheng Li}}, year = {2025}, eprint = {2501.01149v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.01149v3}, note = {First published: 2025-01-02; Recorded arXiv version: v3; Recorded version updated: 2026-01-12T07:01:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.04575", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.04575"}} @misc{arxiv_2501_04575, title = {{InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection}}, author = {{Yuhang Liu} and {Pengxiang Li} and {Zishu Wei} and {Congkai Xie} and {Xueyu Hu} and {Xinchen Xu} and {Shengyu Zhang} and {Xiaotian Han} and {Hongxia Yang} and {Fei Wu}}, year = {2025}, eprint = {2501.04575v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.04575v1}, note = {First published: 2025-01-08; Recorded arXiv version: v1; Recorded version updated: 2025-01-08T15:45:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.07572", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.07572"}} @misc{arxiv_2501_07572, title = {{WebWalker: Benchmarking LLMs in Web Traversal}}, author = {{Jialong Wu} and {Wenbiao Yin} and {Yong Jiang} and {Zhenglin Wang} and {Zekun Xi} and {Runnan Fang} and {Linhai Zhang} and {Yulan He} and {Deyu Zhou} and {Pengjun Xie} and {Fei Huang}}, year = {2025}, eprint = {2501.07572v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.07572v3}, note = {First published: 2025-01-13; Recorded arXiv version: v3; Recorded version updated: 2025-08-10T05:59:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.11425", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2501.11425"}} @misc{arxiv_2501_11425, title = {{Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training}}, author = {{Siyu Yuan} and {Zehui Chen} and {Zhiheng Xi} and {Junjie Ye} and {Zhengyin Du} and {Jiecao Chen}}, year = {2025}, eprint = {2501.11425v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.11425v3}, note = {First published: 2025-01-20; Recorded arXiv version: v3; Recorded version updated: 2025-03-24T10:18:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.11733", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.11733"}} @misc{arxiv_2501_11733, title = {{Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks}}, author = {{Zhenhailong Wang} and {Haiyang Xu} and {Junyang Wang} and {Xi Zhang} and {Ming Yan} and {Ji Zhang} and {Fei Huang} and {Heng Ji}}, year = {2025}, eprint = {2501.11733v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.11733v2}, note = {First published: 2025-01-20; Recorded arXiv version: v2; Recorded version updated: 2025-01-28T16:58:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.12326", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.12326"}} @misc{arxiv_2501_12326, title = {{UI-TARS: Pioneering Automated GUI Interaction with Native Agents}}, author = {{Yujia Qin} and {Yining Ye} and {Junjie Fang} and {Haoming Wang} and {Shihao Liang} and {Shizuo Tian} and {Junda Zhang} and {Jiahao Li} and {Yunxin Li} and {Shijue Huang} and {Wanjun Zhong} and {Kuanye Li} and {Jiale Yang} and {Yu Miao} and {Woyu Lin} and {Longxiang Liu} and {Xu Jiang} and {Qianli Ma} and {Jingyu Li} and {Xiaojun Xiao} and {Kai Cai} and {Chuang Li} and {Yaowei Zheng} and {Chaolin Jin} and {Chen Li} and {Xiao Zhou} and {Minchao Wang} and {Haoli Chen} and {Zhaojian Li} and {Haihua Yang} and {Haifeng Liu} and {Feng Lin} and {Tao Peng} and {Xin Liu} and {Guang Shi}}, year = {2025}, eprint = {2501.12326v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.12326v1}, note = {First published: 2025-01-21; Recorded arXiv version: v1; Recorded version updated: 2025-01-21T17:48:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.13896", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.13896"}} @misc{arxiv_2501_13896, title = {{GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration}}, author = {{Yue Fan} and {Handong Zhao} and {Ruiyi Zhang} and {Yu Shen} and {Xin Eric Wang} and {Gang Wu}}, year = {2025}, eprint = {2501.13896v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.13896v2}, note = {First published: 2025-01-23; Recorded arXiv version: v2; Recorded version updated: 2025-01-27T18:58:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2501.16150", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2501.16150"}} @misc{arxiv_2501_16150, title = {{A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions}}, author = {{Pascal J. Sager} and {Benjamin Meyer} and {Peng Yan} and {Rebekka von Wartburg-Kottler} and {Layan Etaiwi} and {Aref Enayati} and {Gabriel Nobel} and {Ahmed Abdulkadir} and {Benjamin F. Grewe} and {Thilo Stadelmann}}, year = {2025}, eprint = {2501.16150v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.16150v3}, note = {First published: 2025-01-27; Recorded arXiv version: v3; Recorded version updated: 2026-03-27T07:41:10Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2501.16609", "catalog_id": "arxiv:2501.16609", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2501.16609"}, "publication": {"authors": ["Faria Huq", "Zora Zhiruo Wang", "Frank F. Xu", "Tianyue Ou", "Shuyan Zhou", "Jeffrey P. Bigham", "Graham Neubig"], "date_basis": "The ACL Anthology citation_publication_date is 2025/4, and its visible Month/Year fields state April 2025. Only month precision is supplied; no day is inferred from conference dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-demo.17", "event_dates": null, "evidence_urls": ["https://arxiv.org/abs/2501.16609v4", "https://aclanthology.org/2025.naacl-demo.17/"], "identity_basis": "The retained arXiv v4 abstract page explicitly links this DOI. The ACL publication has the same complete title and the same seven authors in the same order, and describes the same CowPilot human-agent navigation framework. This attaches the proceedings edition to the existing arXiv identity.", "issue": null, "notes": "The April 2025 proceedings edition is distinct from the retained arXiv v4, last revised on 2026-02-27. The publisher abstract has minor wording and typesetting differences from the retained arXiv abstract; neither its text nor its date replaces the original arXiv snapshot or annotation. Exact publication day, numeric volume, issue and series are not established.", "pages": "163-172", "pdf_url": "https://aclanthology.org/2025.naacl-demo.17.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.17/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null}} @misc{arxiv_2501_16609, title = {{CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation}}, author = {{Faria Huq} and {Zora Zhiruo Wang} and {Frank F. Xu} and {Tianyue Ou} and {Shuyan Zhou} and {Jeffrey P. Bigham} and {Graham Neubig}}, year = {2025}, eprint = {2501.16609v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.16609v4}, note = {First published: 2025-01-28; Recorded arXiv version: v4; Recorded version updated: 2026-02-27T05:35:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.01977", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.01977"}} @misc{arxiv_2502_01977, title = {{AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs}}, author = {{Hongxin Li} and {Jingfan Chen} and {Jingran Su} and {Yuntao Chen} and {Qing Li} and {Zhaoxiang Zhang}}, year = {2025}, eprint = {2502.01977v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.01977v2}, note = {First published: 2025-02-04; Recorded arXiv version: v2; Recorded version updated: 2025-06-07T05:23:58Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2502.02955", "catalog_id": "arxiv:2502.02955", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2502.02955"}, "publication": {"authors": ["Qinzhuo Wu", "Wei Liu", "Jian Luan", "Bin Wang"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-long.244", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-long.244/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "4760-4775", "pdf_url": "https://aclanthology.org/2025.naacl-long.244.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-long.244/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2502_02955, title = {{ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation}}, author = {{Qinzhuo Wu} and {Wei Liu} and {Jian Luan} and {Bin Wang}}, year = {2025}, eprint = {2502.02955v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.02955v1}, note = {First published: 2025-02-05; Recorded arXiv version: v1; Recorded version updated: 2025-02-05T07:35:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.02982", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.02982"}} @misc{arxiv_2502_02982, title = {{MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users}}, author = {{Wenhao Wang} and {Mengying Yuan} and {Zijie Yu} and {Guangyi Liu} and {Rui Ye} and {Tian Jin} and {Siheng Chen} and {Yanfeng Wang}}, year = {2025}, eprint = {2502.02982v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.02982v2}, note = {First published: 2025-02-05; Recorded arXiv version: v2; Recorded version updated: 2025-05-20T07:03:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.06395", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.06395"}} @misc{arxiv_2502_06395, title = {{AppVLM: A Lightweight Vision Language Model for Online App Control}}, author = {{Georgios Papoudakis} and {Thomas Coste} and {Zhihao Wu} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2025}, eprint = {2502.06395v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.06395v1}, note = {First published: 2025-02-10; Recorded arXiv version: v1; Recorded version updated: 2025-02-10T12:32:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.07942", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.07942"}} @misc{arxiv_2502_07942, title = {{Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs}}, author = {{Ruichen Zhang} and {Mufan Qiu} and {Zhen Tan} and {Mohan Zhang} and {Vincent Lu} and {Jie Peng} and {Kaidi Xu} and {Leandro Z. Agudelo} and {Peter Qian} and {Tianlong Chen}}, year = {2025}, eprint = {2502.07942v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.07942v2}, note = {First published: 2025-02-11; Recorded arXiv version: v2; Recorded version updated: 2025-03-06T19:40:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.07949", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.07949"}} @misc{arxiv_2502_07949, title = {{Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning}}, author = {{Qingyuan Wu} and {Jianheng Liu} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2025}, eprint = {2502.07949v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.07949v2}, note = {First published: 2025-02-11; Recorded arXiv version: v2; Recorded version updated: 2025-05-20T19:54:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.08047", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.08047"}} @misc{arxiv_2502_08047, title = {{WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point}}, author = {{Henry Hengyuan Zhao} and {Kaiming Yang} and {Wendi Yu} and {Difei Gao} and {Mike Zheng Shou}}, year = {2025}, eprint = {2502.08047v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.08047v5}, note = {First published: 2025-02-12; Recorded arXiv version: v5; Recorded version updated: 2026-05-23T20:19:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.08226", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.08226"}} @misc{arxiv_2502_08226, title = {{TRISHUL: Towards Region Identification and Screen Hierarchy Understanding for Large VLM based GUI Agents}}, author = {{Kunal Singh} and {Shreyas Singh} and {Mukund Khanna}}, year = {2025}, eprint = {2502.08226v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.08226v2}, note = {First published: 2025-02-12; Recorded arXiv version: v2; Recorded version updated: 2025-02-14T06:23:57Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2502.11357", "catalog_id": "arxiv:2502.11357", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2502.11357"}, "publication": {"authors": ["Vardaan Pahuja", "Yadong Lu", "Corby Rosset", "Boyu Gou", "Arindam Mitra", "Spencer Whitehead", "Yu Su", "Ahmed Awadallah"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.326", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.326/", "https://aclanthology.org/2025.findings-acl.326.pdf"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. Landing-page citation metadata gives Ahmed Hassan for the final author, while the supplied BibTeX expands the name to Ahmed Hassan Awadallah; the PDF uses Ahmed Awadallah.", "pages": "6300-6323", "pdf_url": "https://aclanthology.org/2025.findings-acl.326.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.326/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2502_11357, title = {{Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents}}, author = {{Vardaan Pahuja} and {Yadong Lu} and {Corby Rosset} and {Boyu Gou} and {Arindam Mitra} and {Spencer Whitehead} and {Yu Su} and {Ahmed Awadallah}}, year = {2025}, eprint = {2502.11357v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.11357v4}, note = {First published: 2025-02-17; Recorded arXiv version: v4; Recorded version updated: 2025-05-30T02:30:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.13053", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.13053"}} @misc{arxiv_2502_13053, title = {{Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks}}, author = {{Yurun Chen} and {Xavier Hu} and {Keting Yin} and {Juncheng Li} and {Shengyu Zhang}}, year = {2025}, eprint = {2502.13053v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.13053v3}, note = {First published: 2025-02-18; Recorded arXiv version: v3; Recorded version updated: 2025-08-06T07:04:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.14282", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.14282"}} @misc{arxiv_2502_14282, title = {{PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC}}, author = {{Haowei Liu} and {Xi Zhang} and {Haiyang Xu} and {Yuyang Wanyan} and {Junyang Wang} and {Ming Yan} and {Ji Zhang} and {Chunfeng Yuan} and {Changsheng Xu} and {Weiming Hu} and {Fei Huang}}, year = {2025}, eprint = {2502.14282v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.14282v2}, note = {First published: 2025-02-20; Recorded arXiv version: v2; Recorded version updated: 2025-02-21T02:54:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.15760", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.15760"}} @misc{arxiv_2502_15760, title = {{Digi-Q: Learning Q-Value Functions for Training Device-Control Agents}}, author = {{Hao Bai} and {Yifei Zhou} and {Li Erran Li} and {Sergey Levine} and {Aviral Kumar}}, year = {2025}, eprint = {2502.15760v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.15760v1}, note = {First published: 2025-02-13; Recorded arXiv version: v1; Recorded version updated: 2025-02-13T18:55:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.17110", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.17110"}} @misc{arxiv_2502_17110, title = {{Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation}}, author = {{Junyang Wang} and {Haiyang Xu} and {Xi Zhang} and {Ming Yan} and {Ji Zhang} and {Fei Huang} and {Jitao Sang}}, year = {2025}, eprint = {2502.17110v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.17110v3}, note = {First published: 2025-02-24; Recorded arXiv version: v3; Recorded version updated: 2025-06-03T08:37:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.17903", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.17903"}} @misc{arxiv_2502_17903, title = {{Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption}}, author = {{Lars Krupp} and {Daniel Geißler} and {Paul Lukowicz} and {Jakob Karolus}}, year = {2025}, eprint = {2502.17903v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.17903v1}, note = {First published: 2025-02-25; Recorded arXiv version: v1; Recorded version updated: 2025-02-25T06:58:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.18525", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.18525"}} @misc{arxiv_2502_18525, title = {{Programming with Pixels: Can Computer-Use Agents do Software Engineering?}}, author = {{Pranjal Aggarwal} and {Sean Welleck}}, year = {2025}, eprint = {2502.18525v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.18525v2}, note = {First published: 2025-02-24; Recorded arXiv version: v2; Recorded version updated: 2025-10-03T02:09:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.18906", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.18906"}} @misc{arxiv_2502_18906, title = {{VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model}}, author = {{Jiani Zheng} and {Lu Wang} and {Fangkai Yang} and {Chaoyun Zhang} and {Lingrui Mei} and {Wenjie Yin} and {Qingwei Lin} and {Dongmei Zhang} and {Saravan Rajmohan} and {Qi Zhang}}, year = {2025}, eprint = {2502.18906v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.18906v1}, note = {First published: 2025-02-26; Recorded arXiv version: v1; Recorded version updated: 2025-02-26T07:52:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2502.20383", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.20383"}} @misc{arxiv_2502_20383, title = {{Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis}}, author = {{Jeffrey Yang Fan Chiang} and {Seungjae Lee} and {Jia-Bin Huang} and {Furong Huang} and {Yizheng Chen}}, year = {2025}, eprint = {2502.20383v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.20383v3}, note = {First published: 2025-02-27; Recorded arXiv version: v3; Recorded version updated: 2025-09-21T22:29:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.00401", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.00401"}} @misc{arxiv_2503_00401, title = {{Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks}}, author = {{Zongru Wu} and {Pengzhou Cheng} and {Zheng Wu} and {Tianjie Ju} and {Zhuosheng Zhang} and {Gongshen Liu}}, year = {2025}, eprint = {2503.00401v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.00401v2}, note = {First published: 2025-03-01; Recorded arXiv version: v2; Recorded version updated: 2025-03-04T12:04:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.01861", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.01861"}} @misc{arxiv_2503_01861, title = {{Towards Enterprise-Ready Computer Using Generalist Agent}}, author = {{Sami Marreed} and {Alon Oved} and {Avi Yaeli} and {Segev Shlomov} and {Ido Levy} and {Offer Akrabi} and {Aviad Sela} and {Asaf Adi} and {Nir Mashkif}}, year = {2025}, eprint = {2503.01861v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.01861v3}, note = {First published: 2025-02-24; Recorded arXiv version: v3; Recorded version updated: 2025-07-09T13:52:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.02197", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2503.02197"}} @misc{arxiv_2503_02197, title = {{ATLaS: Agent Tuning via Learning Critical Steps}}, author = {{Zhixun Chen} and {Ming Li} and {Yuxuan Huang} and {Yali Du} and {Meng Fang} and {Tianyi Zhou}}, year = {2025}, eprint = {2503.02197v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02197v2}, note = {First published: 2025-03-04; Recorded arXiv version: v2; Recorded version updated: 2025-06-05T01:42:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.02268", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.02268"}} @misc{arxiv_2503_02268, title = {{AppAgentX: Evolving GUI Agents as Proficient Smartphone Users}}, author = {{Wenjia Jiang} and {Yangyang Zhuang} and {Chenxi Song} and {Xu Yang} and {Joey Tianyi Zhou} and {Chi Zhang}}, year = {2025}, eprint = {2503.02268v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02268v3}, note = {First published: 2025-03-04; Recorded arXiv version: v3; Recorded version updated: 2025-04-15T02:32:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.02403", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.02403"}} @misc{arxiv_2503_02403, title = {{AutoEval: A Practical Framework for Autonomous Evaluation of Mobile Agents}}, author = {{Jiahui Sun} and {Zhichao Hua} and {Yubin Xia}}, year = {2025}, eprint = {2503.02403v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02403v2}, note = {First published: 2025-03-04; Recorded arXiv version: v2; Recorded version updated: 2025-09-24T05:11:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.02682", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2503.02682"}} @misc{arxiv_2503_02682, title = {{MPO: Boosting LLM Agents with Meta Plan Optimization}}, author = {{Weimin Xiong} and {Yifan Song} and {Qingxiu Dong} and {Bingchan Zhao} and {Feifan Song} and {Xun Wang} and {Sujian Li}}, year = {2025}, eprint = {2503.02682v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02682v2}, note = {First published: 2025-03-04; Recorded arXiv version: v2; Recorded version updated: 2025-09-10T16:45:42Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2503.02950", "catalog_id": "arxiv:2503.02950", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2503.02950"}, "publication": {"authors": ["Danqing Zhang", "Balaji Rama", "Jingyi Ni", "Shiying He", "Fu Zhao", "Kunyu Chen", "Arnold Chen", "Junyu Cao"], "date_basis": "Explicit publisher citation_publication_date: 2025/4. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 4], "doi": "10.18653/v1/2025.naacl-demo.36", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.naacl-demo.36/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "449-455", "pdf_url": "https://aclanthology.org/2025.naacl-demo.36.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications", "type": "conference-paper", "url": "https://aclanthology.org/2025.naacl-demo.36/", "venue": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", "volume": null}} @misc{arxiv_2503_02950, title = {{LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications}}, author = {{Danqing Zhang} and {Balaji Rama} and {Jingyi Ni} and {Shiying He} and {Fu Zhao} and {Kunyu Chen} and {Arnold Chen} and {Junyu Cao}}, year = {2025}, eprint = {2503.02950v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02950v2}, note = {First published: 2025-03-04; Recorded arXiv version: v2; Recorded version updated: 2025-05-06T06:42:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.03196", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.03196"}} @misc{arxiv_2503_03196, title = {{SpiritSight Agent: Advanced GUI Agent with One Look}}, author = {{Zhiyuan Huang} and {Ziming Cheng} and {Junting Pan} and {Zhaohui Hou} and {Mingjie Zhan}}, year = {2025}, eprint = {2503.03196v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.03196v2}, note = {First published: 2025-03-05; Recorded arXiv version: v2; Recorded version updated: 2025-04-16T15:34:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.03743", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.03743"}} @misc{arxiv_2503_03743, title = {{CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning}}, author = {{Yuqi Zhou} and {Shuai Wang} and {Sunhao Dai} and {Qinglin Jia} and {Zhaocheng Du} and {Zhenhua Dong} and {Jun Xu}}, year = {2025}, eprint = {2503.03743v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.03743v1}, note = {First published: 2025-03-05; Recorded arXiv version: v1; Recorded version updated: 2025-03-05T18:56:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.04730", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.04730"}} @misc{arxiv_2503_04730, title = {{WinClick: GUI Grounding with Multimodal Large Language Models}}, author = {{Zheng Hui} and {Yinheng Li} and {Dan zhao} and {Tianyi Chen} and {Colby Banbury} and {Kazuhito Koishida}}, year = {2025}, eprint = {2503.04730v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.04730v1}, note = {First published: 2025-01-27; Recorded arXiv version: v1; Recorded version updated: 2025-01-27T08:29:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.04957", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.04957"}} @misc{arxiv_2503_04957, title = {{SafeArena: Evaluating the Safety of Autonomous Web Agents}}, author = {{Ada Defne Tur} and {Nicholas Meade} and {Xing Han Lù} and {Alejandra Zambrano} and {Arkil Patel} and {Esin Durmus} and {Spandana Gella} and {Karolina Stańczak} and {Siva Reddy}}, year = {2025}, eprint = {2503.04957v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.04957v1}, note = {First published: 2025-03-06; Recorded arXiv version: v1; Recorded version updated: 2025-03-06T20:43:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.05143", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.05143"}} @misc{arxiv_2503_05143, title = {{FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data}}, author = {{Wenhao Wang} and {Zijie Yu} and {Rui Ye} and {Jianqing Zhang} and {Siheng Chen} and {Yanfeng Wang}}, year = {2025}, eprint = {2503.05143v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.05143v1}, note = {First published: 2025-03-07; Recorded arXiv version: v1; Recorded version updated: 2025-03-07T04:52:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.06470", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.06470"}} @misc{arxiv_2503_06470, title = {{Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems}}, author = {{Fei Tang} and {Yongliang Shen} and {Hang Zhang} and {Siqi Chen} and {Guiyang Hou} and {Wenqi Zhang} and {Wenqiao Zhang} and {Kaitao Song} and {Weiming Lu} and {Yueting Zhuang}}, year = {2025}, eprint = {2503.06470v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.06470v1}, note = {First published: 2025-03-09; Recorded arXiv version: v1; Recorded version updated: 2025-03-09T06:14:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.07919", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.07919"}} @misc{arxiv_2503_07919, title = {{BEARCUBS: A benchmark for computer-using web agents}}, author = {{Yixiao Song} and {Katherine Thai} and {Chau Minh Pham} and {Yapei Chang} and {Mazin Nadaf} and {Mohit Iyyer}}, year = {2025}, eprint = {2503.07919v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.07919v3}, note = {First published: 2025-03-10; Recorded arXiv version: v3; Recorded version updated: 2025-07-24T17:45:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.09241", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.09241"}} @misc{arxiv_2503_09241, title = {{In-Context Defense in Computer Agents: An Empirical Study}}, author = {{Pei Yang} and {Hai Ci} and {Mike Zheng Shou}}, year = {2025}, eprint = {2503.09241v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.09241v1}, note = {First published: 2025-03-12; Recorded arXiv version: v1; Recorded version updated: 2025-03-12T10:38:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.09263", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.09263"}} @misc{arxiv_2503_09263, title = {{COLA: A Scalable Multi-Agent Framework For Windows UI Task Automation}}, author = {{Di Zhao} and {Longhui Ma} and {Siwei Wang} and {Miao Wang} and {Zhao Lv}}, year = {2025}, eprint = {2503.09263v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.09263v1}, note = {First published: 2025-03-12; Recorded arXiv version: v1; Recorded version updated: 2025-03-12T11:03:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.09572", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.09572"}} @misc{arxiv_2503_09572, title = {{Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks}}, author = {{Lutfi Eren Erdogan} and {Nicholas Lee} and {Sehoon Kim} and {Suhong Moon} and {Hiroki Furuta} and {Gopala Anumanchipalli} and {Kurt Keutzer} and {Amir Gholami}}, year = {2025}, eprint = {2503.09572v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.09572v3}, note = {First published: 2025-03-12; Recorded arXiv version: v3; Recorded version updated: 2025-04-22T17:56:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.09780", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.09780"}} @misc{arxiv_2503_09780, title = {{AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents}}, author = {{Arman Zharmagambetov} and {Chuan Guo} and {Ivan Evtimov} and {Maya Pavlova} and {Ruslan Salakhutdinov} and {Kamalika Chaudhuri}}, year = {2025}, eprint = {2503.09780v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.09780v3}, note = {First published: 2025-03-12; Recorded arXiv version: v3; Recorded version updated: 2025-10-01T23:55:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.11069", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.11069"}} @misc{arxiv_2503_11069, title = {{API Agents vs. GUI Agents: Divergence and Convergence}}, author = {{Chaoyun Zhang} and {Shilin He} and {Liqun Li} and {Si Qin} and {Yu Kang} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang}}, year = {2025}, eprint = {2503.11069v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.11069v2}, note = {First published: 2025-03-14; Recorded arXiv version: v2; Recorded version updated: 2025-06-23T13:01:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.11170", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.11170"}} @misc{arxiv_2503_11170, title = {{DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents}}, author = {{Yibin Xu} and {Liang Yang} and {Hao Chen} and {Hua Wang} and {Zhi Chen} and {Yaohua Tang}}, year = {2025}, eprint = {2503.11170v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.11170v1}, note = {First published: 2025-03-14; Recorded arXiv version: v1; Recorded version updated: 2025-03-14T08:16:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.12532", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.12532"}} @misc{arxiv_2503_12532, title = {{STEVE: A Step Verification Pipeline for Computer-use Agent Training}}, author = {{Fanbin Lu} and {Zhisheng Zhong} and {Ziqin Wei} and {Shu Liu} and {Chi-Wing Fu} and {Jiaya Jia}}, year = {2025}, eprint = {2503.12532v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.12532v2}, note = {First published: 2025-03-16; Recorded arXiv version: v2; Recorded version updated: 2025-03-24T16:33:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.14021", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.14021"}} @misc{arxiv_2503_14021, title = {{MP-GUI: Modality Perception with MLLMs for GUI Understanding}}, author = {{Ziwei Wang} and {Weizhi Chen} and {Leyang Yang} and {Sheng Zhou} and {Shengchu Zhao} and {Hanbei Zhan} and {Jiongchao Jin} and {Liangcheng Li} and {Zirui Shao} and {Jiajun Bu}}, year = {2025}, eprint = {2503.14021v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.14021v1}, note = {First published: 2025-03-18; Recorded arXiv version: v1; Recorded version updated: 2025-03-18T08:32:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.15515", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.15515"}} @misc{arxiv_2503_15515, title = {{Towards Computer-Using Personal Agents}}, author = {{Piero A. Bonatti} and {John Domingue} and {Anna Lisa Gentile} and {Andreas Harth} and {Olaf Hartig} and {Aidan Hogan} and {Katja Hose} and {Ernesto Jimenez-Ruiz} and {Deborah L. McGuinness} and {Chang Sun} and {Ruben Verborgh} and {Jesse Wright}}, year = {2025}, eprint = {2503.15515v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.15515v1}, note = {First published: 2025-01-31; Recorded arXiv version: v1; Recorded version updated: 2025-01-31T12:26:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.15661", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.15661"}} @misc{arxiv_2503_15661, title = {{UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction}}, author = {{Shravan Nayak} and {Xiangru Jian} and {Kevin Qinghong Lin} and {Juan A. Rodriguez} and {Montek Kalsi} and {Rabiul Awal} and {Nicolas Chapados} and {M. Tamer Özsu} and {Aishwarya Agrawal} and {David Vazquez} and {Christopher Pal} and {Perouz Taslakian} and {Spandana Gella} and {Sai Rajeswar}}, year = {2025}, eprint = {2503.15661v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.15661v2}, note = {First published: 2025-03-19; Recorded arXiv version: v2; Recorded version updated: 2025-05-06T17:43:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.15937", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.15937"}} @misc{arxiv_2503_15937, title = {{Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment}}, author = {{Gaole Dai} and {Shiqi Jiang} and {Ting Cao} and {Yuanchun Li} and {Yuqing Yang} and {Rui Tan} and {Mo Li} and {Lili Qiu}}, year = {2025}, eprint = {2503.15937v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.15937v5}, note = {First published: 2025-03-20; Recorded arXiv version: v5; Recorded version updated: 2026-02-21T01:36:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.16465", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.16465"}} @misc{arxiv_2503_16465, title = {{OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents}}, author = {{Pengzhou Cheng} and {Zheng Wu} and {Zongru Wu} and {Aston Zhang} and {Zhuosheng Zhang} and {Gongshen Liu}}, year = {2025}, eprint = {2503.16465v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.16465v3}, note = {First published: 2025-02-26; Recorded arXiv version: v3; Recorded version updated: 2025-07-14T15:56:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.16788", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.16788"}} @misc{arxiv_2503_16788, title = {{Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study}}, author = {{Li Zhang} and {Longxi Gao} and {Mengwei Xu}}, year = {2025}, eprint = {2503.16788v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.16788v1}, note = {First published: 2025-03-21; Recorded arXiv version: v1; Recorded version updated: 2025-03-21T01:52:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.17709", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.17709"}} @misc{arxiv_2503_17709, title = {{GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration}}, author = {{Yuchen Sun} and {Shanhui Zhao} and {Tao Yu} and {Hao Wen} and {Samith Va} and {Mengwei Xu} and {Yuanchun Li} and {Chongyang Zhang}}, year = {2025}, eprint = {2503.17709v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.17709v1}, note = {First published: 2025-03-22; Recorded arXiv version: v1; Recorded version updated: 2025-03-22T09:30:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.18492", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.18492"}} @misc{arxiv_2503_18492, title = {{VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verification}}, author = {{Jungjae Lee} and {Dongjae Lee} and {Chihun Choi} and {Youngmin Im} and {Jaeyoung Wi} and {Kihong Heo} and {Sangeun Oh} and {Sunjae Lee} and {Insik Shin}}, year = {2025}, eprint = {2503.18492v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.18492v2}, note = {First published: 2025-03-24; Recorded arXiv version: v2; Recorded version updated: 2025-09-11T04:15:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.19537", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.19537"}} @misc{arxiv_2503_19537, title = {{Agent-Initiated Interaction in Phone UI Automation}}, author = {{Noam Kahlon} and {Guy Rom} and {Anatoly Efros} and {Filippo Galgani} and {Omri Berkovitch} and {Sapir Caduri} and {William E. Bishop} and {Oriana Riva} and {Ido Dagan}}, year = {2025}, eprint = {2503.19537v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.19537v1}, note = {First published: 2025-03-25; Recorded arXiv version: v1; Recorded version updated: 2025-03-25T10:46:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.20279", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.20279"}} @misc{arxiv_2503_20279, title = {{sudo rm -rf agentic\_security}}, author = {{Sejin Lee} and {Jian Kim} and {Haon Park} and {Ashkan Yousefpour} and {Sangyoon Yu} and {Min Song}}, year = {2025}, eprint = {2503.20279v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.20279v3}, note = {First published: 2025-03-26; Recorded arXiv version: v3; Recorded version updated: 2025-06-08T05:39:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.20978", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.20978"}} @misc{arxiv_2503_20978, title = {{ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction}}, author = {{Yiqiao Jin} and {Stefano Petrangeli} and {Yu Shen} and {Gang Wu}}, year = {2025}, eprint = {2503.20978v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.20978v1}, note = {First published: 2025-03-26; Recorded arXiv version: v1; Recorded version updated: 2025-03-26T20:41:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.21620", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.21620"}} @misc{arxiv_2503_21620, title = {{UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning}}, author = {{Zhengxi Lu} and {Yuxiang Chai} and {Yaxuan Guo} and {Xi Yin} and {Liang Liu} and {Hao Wang} and {Han Xiao} and {Shuai Ren} and {Guanjing Xiong} and {Hongsheng Li}}, year = {2025}, eprint = {2503.21620v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.21620v5}, note = {First published: 2025-03-27; Recorded arXiv version: v5; Recorded version updated: 2025-05-24T08:46:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.22738", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.22738"}} @misc{arxiv_2503_22738, title = {{ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning}}, author = {{Zhaorun Chen} and {Mintong Kang} and {Bo Li}}, year = {2025}, eprint = {2503.22738v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.22738v2}, note = {First published: 2025-03-26; Recorded arXiv version: v2; Recorded version updated: 2025-11-27T22:01:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.23350", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.23350"}} @misc{arxiv_2503_23350, title = {{A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models}}, author = {{Liangbo Ning} and {Ziran Liang} and {Zhuohang Jiang} and {Haohao Qu} and {Yujuan Ding} and {Wenqi Fan} and {Xiao-yong Wei} and {Shanru Lin} and {Hui Liu} and {Philip S. Yu} and {Qing Li}}, year = {2025}, eprint = {2503.23350v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.23350v4}, note = {First published: 2025-03-30; Recorded arXiv version: v4; Recorded version updated: 2025-08-05T11:47:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.23434", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.23434"}} @misc{arxiv_2503_23434, title = {{Towards Trustworthy GUI Agents: A Survey}}, author = {{Yucheng Shi} and {Wenhao Yu} and {Jingyuan Huang} and {Wenlin Yao} and {Wenhu Chen} and {Ninghao Liu}}, year = {2025}, eprint = {2503.23434v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.23434v2}, note = {First published: 2025-03-30; Recorded arXiv version: v2; Recorded version updated: 2026-02-24T05:24:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2503.24180", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.24180"}} @misc{arxiv_2503_24180, title = {{Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions}}, author = {{Ziming Cheng} and {Zhiyuan Huang} and {Junting Pan} and {Zhaohui Hou} and {Mingjie Zhan}}, year = {2025}, eprint = {2503.24180v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.24180v2}, note = {First published: 2025-03-31; Recorded arXiv version: v2; Recorded version updated: 2025-08-24T08:39:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.00906", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.00906"}} @misc{arxiv_2504_00906, title = {{Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents}}, author = {{Saaket Agashe} and {Kyle Wong} and {Vincent Tu} and {Jiachen Yang} and {Ang Li} and {Xin Eric Wang}}, year = {2025}, eprint = {2504.00906v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.00906v1}, note = {First published: 2025-04-01; Recorded arXiv version: v1; Recorded version updated: 2025-04-01T15:40:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.01382", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.01382"}} @misc{arxiv_2504_01382, title = {{An Illusion of Progress? Assessing the Current State of Web Agents}}, author = {{Tianci Xue} and {Weijian Qi} and {Tianneng Shi} and {Chan Hee Song} and {Boyu Gou} and {Dawn Song} and {Huan Sun} and {Yu Su}}, year = {2025}, eprint = {2504.01382v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.01382v4}, note = {First published: 2025-04-02; Recorded arXiv version: v4; Recorded version updated: 2025-10-08T02:22:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.01495", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.01495"}} @misc{arxiv_2504_01495, title = {{Are Autonomous Web Agents Good Testers?}}, author = {{Antoine Chevrot} and {Alexandre Vernotte} and {Jean-Rémy Falleri} and {Xavier Blanc} and {Bruno Legeard}}, year = {2025}, eprint = {2504.01495v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.01495v1}, note = {First published: 2025-04-02; Recorded arXiv version: v1; Recorded version updated: 2025-04-02T08:48:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.02357", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.02357"}} @misc{arxiv_2504_02357, title = {{ReuseDroid: A VLM-empowered Android UI Test Migrator Boosted by Active Feedback}}, author = {{Xiaolei Li} and {Jialun Cao} and {Yepang Liu} and {Shing-Chi Cheung} and {Hailong Wang}}, year = {2025}, eprint = {2504.02357v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.02357v1}, note = {First published: 2025-04-03; Recorded arXiv version: v1; Recorded version updated: 2025-04-03T07:45:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.04716", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.04716"}} @misc{arxiv_2504_04716, title = {{On the Robustness of GUI Grounding Models Against Image Attacks}}, author = {{Haoren Zhao} and {Tianyi Chen} and {Zhen Wang}}, year = {2025}, eprint = {2504.04716v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.04716v1}, note = {First published: 2025-04-07; Recorded arXiv version: v1; Recorded version updated: 2025-04-07T03:58:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.07079", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.07079"}} @misc{arxiv_2504_07079, title = {{SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills}}, author = {{Boyuan Zheng} and {Michael Y. Fatemi} and {Xiaolong Jin} and {Zora Zhiruo Wang} and {Apurva Gandhi} and {Yueqi Song} and {Yu Gu} and {Jayanth Srinivasa} and {Gaowen Liu} and {Graham Neubig} and {Yu Su}}, year = {2025}, eprint = {2504.07079v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.07079v1}, note = {First published: 2025-04-09; Recorded arXiv version: v1; Recorded version updated: 2025-04-09T17:51:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.07981", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.07981"}} @misc{arxiv_2504_07981, title = {{ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use}}, author = {{Kaixin Li} and {Ziyang Meng} and {Hongzhan Lin} and {Ziyang Luo} and {Yuchen Tian} and {Jing Ma} and {Zhiyong Huang} and {Tat-Seng Chua}}, year = {2025}, eprint = {2504.07981v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.07981v1}, note = {First published: 2025-04-04; Recorded arXiv version: v1; Recorded version updated: 2025-04-04T14:25:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.08942", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.08942"}} @misc{arxiv_2504_08942, title = {{AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories}}, author = {{Xing Han Lù} and {Amirhossein Kazemnejad} and {Nicholas Meade} and {Arkil Patel} and {Dongchan Shin} and {Alejandra Zambrano} and {Karolina Stańczak} and {Peter Shaw} and {Christopher J. Pal} and {Siva Reddy}}, year = {2025}, eprint = {2504.08942v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.08942v2}, note = {First published: 2025-04-11; Recorded arXiv version: v2; Recorded version updated: 2025-10-06T15:46:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.09352", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.09352"}} @misc{arxiv_2504_09352, title = {{Explorer: Robust Collection of Interactable GUI Elements}}, author = {{Iason Chaimalas} and {Arnas Vyšniauskas} and {Gabriel Brostow}}, year = {2025}, eprint = {2504.09352v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.09352v1}, note = {First published: 2025-04-12; Recorded arXiv version: v1; Recorded version updated: 2025-04-12T22:02:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.10127", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.10127"}} @misc{arxiv_2504_10127, title = {{Breaking the Data Barrier -- Building GUI Agents Through Task Generalization}}, author = {{Junlei Zhang} and {Zichen Ding} and {Chang Ma} and {Zijie Chen} and {Qiushi Sun} and {Zhenzhong Lan} and {Junxian He}}, year = {2025}, eprint = {2504.10127v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.10127v2}, note = {First published: 2025-04-14; Recorded arXiv version: v2; Recorded version updated: 2025-04-15T17:13:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.10445", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.10445"}} @misc{arxiv_2504_10445, title = {{RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users}}, author = {{Suyu Ye} and {Haojun Shi} and {Darren Shih} and {Hyokun Yun} and {Tanya Roosta} and {Tianmin Shu}}, year = {2025}, eprint = {2504.10445v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.10445v2}, note = {First published: 2025-04-14; Recorded arXiv version: v2; Recorded version updated: 2025-12-01T15:22:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.10458", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.10458"}} @misc{arxiv_2504_10458, title = {{GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents}}, author = {{Run Luo} and {Lu Wang} and {Wanwei He} and {Longze Chen} and {Jiaming Li} and {Xiaobo Xia}}, year = {2025}, eprint = {2504.10458v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.10458v4}, note = {First published: 2025-04-14; Recorded arXiv version: v4; Recorded version updated: 2025-10-01T04:55:20Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2504.11257", "catalog_id": "arxiv:2504.11257", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2504.11257"}, "publication": {"authors": ["Xinyi Liu", "Xiaoyi Zhang", "Ziyun Zhang", "Yan Lu"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.809", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.809/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "15668-15684", "pdf_url": "https://aclanthology.org/2025.findings-acl.809.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.809/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}} @misc{arxiv_2504_11257, title = {{UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis}}, author = {{Xinyi Liu} and {Xiaoyi Zhang} and {Ziyun Zhang} and {Yan Lu}}, year = {2025}, eprint = {2504.11257v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.11257v4}, note = {First published: 2025-04-15; Recorded arXiv version: v4; Recorded version updated: 2025-07-30T13:57:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.11281", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.11281"}} @misc{arxiv_2504_11281, title = {{The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections}}, author = {{Chaoran Chen} and {Zhiping Zhang} and {Bingcan Guo} and {Shang Ma} and {Ibrahim Khalilov} and {Simret A Gebreegziabher} and {Yanfang Ye} and {Ziang Xiao} and {Yaxing Yao} and {Tianshi Li} and {Toby Jia-Jun Li}}, year = {2025}, eprint = {2504.11281v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.11281v1}, note = {First published: 2025-04-15; Recorded arXiv version: v1; Recorded version updated: 2025-04-15T15:21:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.11675", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.11675"}} @misc{arxiv_2504_11675, title = {{VLM-Fuzz: Vision Language Model Assisted Recursive Depth-first Search Exploration for Effective UI Testing of Android Apps}}, author = {{Biniam Fisseha Demissie} and {Yan Naing Tun} and {Lwin Khin Shar} and {Mariano Ceccato}}, year = {2025}, eprint = {2504.11675v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.11675v1}, note = {First published: 2025-04-16; Recorded arXiv version: v1; Recorded version updated: 2025-04-16T00:19:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.11788", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.11788"}} @misc{arxiv_2504_11788, title = {{WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms}}, author = {{Zhisong Zhang} and {Tianqing Fang} and {Kaixin Ma} and {Wenhao Yu} and {Hongming Zhang} and {Haitao Mi} and {Dong Yu}}, year = {2025}, eprint = {2504.11788v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.11788v3}, note = {First published: 2025-04-16; Recorded arXiv version: v3; Recorded version updated: 2026-01-15T02:00:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.12679", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.12679"}} @misc{arxiv_2504_12679, title = {{TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents}}, author = {{Bofei Zhang} and {Zirui Shang} and {Zhi Gao} and {Wang Zhang} and {Rui Xie} and {Xiaojian Ma} and {Tao Yuan} and {Xinxiao Wu} and {Song-Chun Zhu} and {Qing Li}}, year = {2025}, eprint = {2504.12679v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.12679v4}, note = {First published: 2025-04-17; Recorded arXiv version: v4; Recorded version updated: 2025-12-04T15:01:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.13805", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.13805"}} @misc{arxiv_2504_13805, title = {{LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark}}, author = {{Guangyi Liu} and {Pengxiang Zhao} and {Liang Liu} and {Zhiming Chen} and {Yuxiang Chai} and {Shuai Ren} and {Hao Wang} and {Shibo He} and {Wenchao Meng}}, year = {2025}, eprint = {2504.13805v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.13805v1}, note = {First published: 2025-04-18; Recorded arXiv version: v1; Recorded version updated: 2025-04-18T17:13:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.13865", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.13865"}} @misc{arxiv_2504_13865, title = {{A Survey on (M)LLM-Based GUI Agents}}, author = {{Fei Tang} and {Haolei Xu} and {Hang Zhang} and {Siqi Chen} and {Xingyu Wu} and {Yongliang Shen} and {Wenqi Zhang} and {Guiyang Hou} and {Zeqi Tan} and {Yuchen Yan} and {Kaitao Song} and {Jian Shao} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang}}, year = {2025}, eprint = {2504.13865v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.13865v2}, note = {First published: 2025-03-27; Recorded arXiv version: v2; Recorded version updated: 2025-06-04T17:29:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.13936", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.13936"}} @misc{arxiv_2504_13936, title = {{ViMo: A Generative Visual GUI World Model for App Agents}}, author = {{Dezhao Luo} and {Bohan Tang} and {Kang Li} and {Georgios Papoudakis} and {Jifei Song} and {Shaogang Gong} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2025}, eprint = {2504.13936v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.13936v2}, note = {First published: 2025-04-15; Recorded arXiv version: v2; Recorded version updated: 2025-05-20T14:11:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.14064", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.14064"}} @misc{arxiv_2504_14064, title = {{DoomArena: A framework for Testing AI Agents Against Evolving Security Threats}}, author = {{Leo Boisvert} and {Mihir Bansal} and {Chandra Kiran Reddy Evuru} and {Gabriel Huang} and {Abhay Puri} and {Avinandan Bose} and {Maryam Fazel} and {Quentin Cappart} and {Jason Stanley} and {Alexandre Lacoste} and {Alexandre Drouin} and {Krishnamurthy Dvijotham}}, year = {2025}, eprint = {2504.14064v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.14064v3}, note = {First published: 2025-04-18; Recorded arXiv version: v3; Recorded version updated: 2025-10-07T13:10:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.14239", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.14239"}} @misc{arxiv_2504_14239, title = {{InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners}}, author = {{Yuhang Liu} and {Pengxiang Li} and {Congkai Xie} and {Xavier Hu} and {Xiaotian Han} and {Shengyu Zhang} and {Hongxia Yang} and {Fei Wu}}, year = {2025}, eprint = {2504.14239v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.14239v1}, note = {First published: 2025-04-19; Recorded arXiv version: v1; Recorded version updated: 2025-04-19T09:25:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.14603", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.14603"}} @misc{arxiv_2504_14603, title = {{UFO2: The Desktop AgentOS}}, author = {{Chaoyun Zhang} and {He Huang} and {Chiming Ni} and {Jian Mu} and {Si Qin} and {Shilin He} and {Lu Wang} and {Fangkai Yang} and {Pu Zhao} and {Chao Du} and {Liqun Li} and {Yu Kang} and {Zhao Jiang} and {Suzhen Zheng} and {Rujia Wang} and {Jiaxu Qian} and {Minghua Ma} and {Jian-Guang Lou} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang}}, year = {2025}, eprint = {2504.14603v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.14603v2}, note = {First published: 2025-04-20; Recorded arXiv version: v2; Recorded version updated: 2025-04-25T05:14:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.16073", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.16073"}} @misc{arxiv_2504_16073, title = {{Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation}}, author = {{Zhiyuan Hu} and {Shiyun Xiong} and {Yifan Zhang} and {See-Kiong Ng} and {Anh Tuan Luu} and {Bo An} and {Shuicheng Yan} and {Bryan Hooi}}, year = {2025}, eprint = {2504.16073v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.16073v1}, note = {First published: 2025-04-22; Recorded arXiv version: v1; Recorded version updated: 2025-04-22T17:52:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.16419", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.16419"}} @misc{arxiv_2504_16419, title = {{PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels}}, author = {{Qi Yang} and {Weichen Bi} and {Haiyang Shen} and {Yaoqi Guo} and {Yun Ma}}, year = {2025}, eprint = {2504.16419v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.16419v2}, note = {First published: 2025-04-23; Recorded arXiv version: v2; Recorded version updated: 2025-04-27T06:52:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.17934", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.17934"}} @misc{arxiv_2504_17934, title = {{Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents}}, author = {{Chaoran Chen} and {Zhiping Zhang} and {Ibrahim Khalilov} and {Bingcan Guo} and {Simret A Gebreegziabher} and {Yanfang Ye} and {Ziang Xiao} and {Yaxing Yao} and {Tianshi Li} and {Toby Jia-Jun Li}}, year = {2025}, eprint = {2504.17934v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.17934v2}, note = {First published: 2025-04-24; Recorded arXiv version: v2; Recorded version updated: 2025-06-05T12:40:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.18575", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.18575"}} @misc{arxiv_2504_18575, title = {{WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks}}, author = {{Ivan Evtimov} and {Arman Zharmagambetov} and {Aaron Grattafiori} and {Chuan Guo} and {Kamalika Chaudhuri}}, year = {2025}, eprint = {2504.18575v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.18575v3}, note = {First published: 2025-04-22; Recorded arXiv version: v3; Recorded version updated: 2025-05-16T22:42:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.19838", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.19838"}} @misc{arxiv_2504_19838, title = {{LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects}}, author = {{Guangyi Liu} and {Pengxiang Zhao} and {Yaozhen Liang} and {Liang Liu} and {Yaxuan Guo} and {Han Xiao} and {Weifeng Lin} and {Yuxiang Chai} and {Yue Han} and {Shuai Ren} and {Hao Wang} and {Xiaoyu Liang} and {WenHao Wang} and {Tianze Wu} and {Zhengxi Lu} and {Siheng Chen} and {LiLinghao} and {Hao Wang} and {Guanjing Xiong} and {Yong Liu} and {Hongsheng Li}}, year = {2025}, eprint = {2504.19838v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.19838v3}, note = {First published: 2025-04-28; Recorded arXiv version: v3; Recorded version updated: 2025-11-17T15:51:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.20464", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.20464"}} @misc{arxiv_2504_20464, title = {{A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning}}, author = {{Jiahao Li} and {Kaer Huang}}, year = {2025}, eprint = {2504.20464v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.20464v2}, note = {First published: 2025-04-29; Recorded arXiv version: v2; Recorded version updated: 2025-05-13T01:59:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.21024", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.21024"}} @misc{arxiv_2504_21024, title = {{WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model}}, author = {{Tianqing Fang} and {Hongming Zhang} and {Zhisong Zhang} and {Kaixin Ma} and {Wenhao Yu} and {Haitao Mi} and {Dong Yu}}, year = {2025}, eprint = {2504.21024v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.21024v2}, note = {First published: 2025-04-23; Recorded arXiv version: v2; Recorded version updated: 2025-08-21T05:55:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2504.21776", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2504.21776"}} @misc{arxiv_2504_21776, title = {{WebThinker: Empowering Large Reasoning Models with Deep Research Capability}}, author = {{Xiaoxi Li} and {Jiajie Jin} and {Guanting Dong} and {Hongjin Qian} and {Yongkang Wu} and {Ji-Rong Wen} and {Yutao Zhu} and {Zhicheng Dou}}, year = {2025}, eprint = {2504.21776v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.21776v2}, note = {First published: 2025-04-30; Recorded arXiv version: v2; Recorded version updated: 2025-10-13T12:40:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.00416", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.00416"}} @misc{arxiv_2505_00416, title = {{ScaleTrack: Scaling and back-tracking Automated GUI Agents}}, author = {{Jing Huang} and {Zhixiong Zeng} and {Wenkang Han} and {Yufeng Zhong} and {Liming Zheng} and {Shuai Fu} and {Jingyuan Chen} and {Lin Ma}}, year = {2025}, eprint = {2505.00416v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.00416v1}, note = {First published: 2025-05-01; Recorded arXiv version: v1; Recorded version updated: 2025-05-01T09:27:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.00684", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.00684"}} @misc{arxiv_2505_00684, title = {{Visual Test-time Scaling for GUI Agent Grounding}}, author = {{Tiange Luo} and {Lajanugen Logeswaran} and {Justin Johnson} and {Honglak Lee}}, year = {2025}, eprint = {2505.00684v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.00684v2}, note = {First published: 2025-05-01; Recorded arXiv version: v2; Recorded version updated: 2025-07-14T17:45:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.03570", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.03570"}} @misc{arxiv_2505_03570, title = {{OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents}}, author = {{Mariya Davydova} and {Daniel Jeffries} and {Patrick Barker} and {Arturo Márquez Flores} and {Sinéad Ryan}}, year = {2025}, eprint = {2505.03570v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.03570v1}, note = {First published: 2025-05-06; Recorded arXiv version: v1; Recorded version updated: 2025-05-06T14:29:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.05026", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2505.05026"}} @misc{arxiv_2505_05026, title = {{Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding}}, author = {{Jaehyun Jeon} and {Min Soo Kim} and {Jang Han Yoon} and {Sumin Shim} and {Yejin Choi} and {Hanbin Kim} and {Dae Hyun Kim} and {Youngjae Yu}}, year = {2025}, eprint = {2505.05026v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.05026v5}, note = {First published: 2025-05-08; Recorded arXiv version: v5; Recorded version updated: 2026-06-04T06:58:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.05440", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.05440"}} @misc{arxiv_2505_05440, title = {{EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation}}, author = {{Biao Yi} and {Xavier Hu} and {Yurun Chen} and {Shengyu Zhang} and {Hongxia Yang} and {Fan Wu}}, year = {2025}, eprint = {2505.05440v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.05440v3}, note = {First published: 2025-05-08; Recorded arXiv version: v3; Recorded version updated: 2025-11-17T09:12:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.09875", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.09875"}} @misc{arxiv_2505_09875, title = {{Characterizing Unintended Consequences in Human-GUI Agent Collaboration for Web Browsing}}, author = {{Shuning Zhang} and {Jingruo Chen} and {Zhiqi Gao} and {Jiajing Gao} and {Xin Yi} and {Hewu Li}}, year = {2025}, eprint = {2505.09875v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.09875v2}, note = {First published: 2025-05-15; Recorded arXiv version: v2; Recorded version updated: 2025-05-16T07:01:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.10593", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.10593"}} @misc{arxiv_2505_10593, title = {{LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps}}, author = {{Shanhui Zhao} and {Hao Wen} and {Wenjie Du} and {Cheng Liang} and {Yunxin Liu} and {Xiaozhou Ye} and {Ye Ouyang} and {Yuanchun Li}}, year = {2025}, eprint = {2505.10593v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.10593v1}, note = {First published: 2025-05-15; Recorded arXiv version: v1; Recorded version updated: 2025-05-15T05:28:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.10831", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.10831"}} @misc{arxiv_2505_10831, title = {{Creating General User Models from Computer Use}}, author = {{Omar Shaikh} and {Shardul Sapkota} and {Shan Rizvi} and {Eric Horvitz} and {Joon Sung Park} and {Diyi Yang} and {Michael S. Bernstein}}, year = {2025}, eprint = {2505.10831v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.10831v3}, note = {First published: 2025-05-16; Recorded arXiv version: v3; Recorded version updated: 2025-09-21T00:03:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.10924", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.10924"}} @misc{arxiv_2505_10924, title = {{A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?}}, author = {{Ada Chen} and {Yongjiang Wu} and {Junyuan Zhang} and {Jingyu Xiao} and {Shu Yang} and {Jen-tse Huang} and {Kun Wang} and {Wenxuan Wang} and {Shuai Wang}}, year = {2025}, eprint = {2505.10924v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.10924v4}, note = {First published: 2025-05-16; Recorded arXiv version: v4; Recorded version updated: 2026-04-29T05:56:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.11891", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.11891"}} @misc{arxiv_2505_11891, title = {{Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents}}, author = {{Weikai Xu} and {Zhizheng Jiang} and {Yuxuan Liu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Yuanchun Li} and {Yunxin Liu} and {Bin Wang} and {Bo An}}, year = {2025}, eprint = {2505.11891v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.11891v3}, note = {First published: 2025-05-17; Recorded arXiv version: v3; Recorded version updated: 2026-02-02T06:55:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.12299", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12299"}} @misc{arxiv_2505_12299, title = {{MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning}}, author = {{Kun Huang} and {Weikai Xu} and {Yuxuan Liu} and {Quandong Wang} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Bin Wang} and {Bo An}}, year = {2025}, eprint = {2505.12299v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12299v4}, note = {First published: 2025-05-18; Recorded arXiv version: v4; Recorded version updated: 2026-03-21T09:25:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.12370", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12370"}} @misc{arxiv_2505_12370, title = {{Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning}}, author = {{Xinbin Yuan} and {Jian Zhang} and {Kaixin Li} and {Zhuoxuan Cai} and {Lujian Yao} and {Jie Chen} and {Enguang Wang} and {Qibin Hou} and {Jinwei Chen} and {Peng-Tao Jiang} and {Bo Li}}, year = {2025}, eprint = {2505.12370v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12370v2}, note = {First published: 2025-05-18; Recorded arXiv version: v2; Recorded version updated: 2025-05-24T03:01:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.12493", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12493"}} @misc{arxiv_2505_12493, title = {{GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning}}, author = {{Longxi Gao} and {Li Zhang} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Mengwei Xu}}, year = {2025}, eprint = {2505.12493v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12493v3}, note = {First published: 2025-05-18; Recorded arXiv version: v3; Recorded version updated: 2025-10-10T09:28:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.12632", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12632"}} @misc{arxiv_2505_12632, title = {{Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents}}, author = {{Yunseok Jang} and {Yeda Song} and {Sungryull Sohn} and {Lajanugen Logeswaran} and {Tiange Luo} and {Dong-Ki Kim} and {Kyunghoon Bae} and {Honglak Lee}}, year = {2025}, eprint = {2505.12632v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12632v1}, note = {First published: 2025-05-19; Recorded arXiv version: v1; Recorded version updated: 2025-05-19T02:39:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.12842", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12842"}} @misc{arxiv_2505_12842, title = {{GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents}}, author = {{Zheng Wu} and {Pengzhou Cheng} and {Zongru Wu} and {Lingzhong Dong} and {Zhuosheng Zhang}}, year = {2025}, eprint = {2505.12842v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12842v4}, note = {First published: 2025-05-19; Recorded arXiv version: v4; Recorded version updated: 2025-11-22T15:07:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.12981", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12981"}} @misc{arxiv_2505_12981, title = {{From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents}}, author = {{Liangxuan Wu} and {Chao Wang} and {Tianming Liu} and {Yanjie Zhao} and {Haoyu Wang}}, year = {2025}, eprint = {2505.12981v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12981v2}, note = {First published: 2025-05-19; Recorded arXiv version: v2; Recorded version updated: 2025-05-20T07:02:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.13076", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.13076"}} @misc{arxiv_2505_13076, title = {{The Hidden Dangers of Browsing AI Agents}}, author = {{Mykyta Mudryi} and {Markiyan Chaklosh} and {Grzegorz Wójcik}}, year = {2025}, eprint = {2505.13076v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.13076v1}, note = {First published: 2025-05-19; Recorded arXiv version: v1; Recorded version updated: 2025-05-19T13:10:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.13227", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.13227"}} @misc{arxiv_2505_13227, title = {{Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis}}, author = {{Tianbao Xie} and {Jiaqi Deng} and {Xiaochuan Li} and {Junlin Yang} and {Haoyuan Wu} and {Jixuan Chen} and {Wenjing Hu} and {Xinyuan Wang} and {Yuhui Xu} and {Zekun Wang} and {Yiheng Xu} and {Junli Wang} and {Doyen Sahoo} and {Tao Yu} and {Caiming Xiong}}, year = {2025}, eprint = {2505.13227v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.13227v3}, note = {First published: 2025-05-19; Recorded arXiv version: v3; Recorded version updated: 2025-10-24T19:08:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.13909", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.13909"}} @misc{arxiv_2505_13909, title = {{Efficient Agent Training for Computer Use}}, author = {{Yanheng He} and {Jiahe Jin} and {Pengfei Liu}}, year = {2025}, eprint = {2505.13909v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.13909v2}, note = {First published: 2025-05-20; Recorded arXiv version: v2; Recorded version updated: 2026-03-03T03:55:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.14141", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.14141"}} @misc{arxiv_2505_14141, title = {{Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent}}, author = {{Fanglin Mo} and {Junzhe Chen} and {Haoxuan Zhu} and {Xuming Hu}}, year = {2025}, eprint = {2505.14141v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.14141v1}, note = {First published: 2025-05-20; Recorded arXiv version: v1; Recorded version updated: 2025-05-20T09:45:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.14289", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.14289"}} @misc{arxiv_2505_14289, title = {{EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks}}, author = {{Yijie Lu} and {Manman Zhao} and {Tianjie Ju} and {Zihe Yan} and {Xinbei Ma} and {Yuan Guo} and {Daizong Ding} and {Gongshen Liu} and {Zhuosheng Zhang}}, year = {2025}, eprint = {2505.14289v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.14289v2}, note = {First published: 2025-05-20; Recorded arXiv version: v2; Recorded version updated: 2026-06-05T10:24:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.14418", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.14418"}} @misc{arxiv_2505_14418, title = {{Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents}}, author = {{Pengzhou Cheng} and {Haowen Hu} and {Zheng Wu} and {Zongru Wu} and {Tianjie Ju} and {Zhuosheng Zhang} and {Gongshen Liu}}, year = {2025}, eprint = {2505.14418v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.14418v3}, note = {First published: 2025-05-20; Recorded arXiv version: v3; Recorded version updated: 2026-06-15T06:42:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.15259", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.15259"}} @misc{arxiv_2505_15259, title = {{ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search}}, author = {{Hyunseok Lee} and {Jeonghoon Kim} and {Beomjun Kim} and {Jihoon Tack} and {Chansong Jo} and {Jaehong Lee} and {Cheonbok Park} and {Sookyo In} and {Jinwoo Shin} and {Kang Min Yoo}}, year = {2025}, eprint = {2505.15259v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.15259v2}, note = {First published: 2025-05-21; Recorded arXiv version: v2; Recorded version updated: 2025-05-24T15:08:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.15277", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.15277"}} @misc{arxiv_2505_15277, title = {{Web-Shepherd: Advancing PRMs for Reinforcing Web Agents}}, author = {{Hyungjoo Chae} and {Sunghwan Kim} and {Junhee Cho} and {Seungone Kim} and {Seungjun Moon} and {Gyeom Hwangbo} and {Dongha Lim} and {Minjin Kim} and {Yeonjun Hwang} and {Minju Gwak} and {Dongwook Choi} and {Minseok Kang} and {Gwanhoon Im} and {ByeongUng Cho} and {Hyojun Kim} and {Jun Hee Han} and {Taeyoon Kwon} and {Minju Kim} and {Beong-woo Kwak} and {Dongjin Kang} and {Jinyoung Yeo}}, year = {2025}, eprint = {2505.15277v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.15277v2}, note = {First published: 2025-05-21; Recorded arXiv version: v2; Recorded version updated: 2025-11-25T21:34:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.15810", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.15810"}} @misc{arxiv_2505_15810, title = {{GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents}}, author = {{Yuqi Zhou} and {Sunhao Dai} and {Shuai Wang} and {Kaiwen Zhou} and {Qinglin Jia} and {Jun Xu}}, year = {2025}, eprint = {2505.15810v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.15810v2}, note = {First published: 2025-05-21; Recorded arXiv version: v2; Recorded version updated: 2025-05-22T11:15:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.16282", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.16282"}} @misc{arxiv_2505_16282, title = {{ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay}}, author = {{Fanbin Lu} and {Zhisheng Zhong} and {Shu Liu} and {Chi-Wing Fu} and {Jiaya Jia}}, year = {2025}, eprint = {2505.16282v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.16282v1}, note = {First published: 2025-05-22; Recorded arXiv version: v1; Recorded version updated: 2025-05-22T06:24:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.16421", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.16421"}} @misc{arxiv_2505_16421, title = {{WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning}}, author = {{Zhepei Wei} and {Wenlin Yao} and {Yao Liu} and {Weizhi Zhang} and {Qin Lu} and {Liang Qiu} and {Changlong Yu} and {Puyang Xu} and {Chao Zhang} and {Bing Yin} and {Hyokun Yun} and {Lihong Li}}, year = {2025}, eprint = {2505.16421v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.16421v2}, note = {First published: 2025-05-22; Recorded arXiv version: v2; Recorded version updated: 2025-10-08T21:16:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.16422", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.16422"}} @misc{arxiv_2505_16422, title = {{Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach}}, author = {{Xiaoran Yin} and {Xu Luo} and {Hao Wu} and {Lianli Gao} and {Jingkuan Song}}, year = {2025}, eprint = {2505.16422v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.16422v3}, note = {First published: 2025-05-22; Recorded arXiv version: v3; Recorded version updated: 2025-09-05T02:24:00Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2505.16827", "catalog_id": "arxiv:2505.16827", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2505.16827"}, "publication": {"authors": ["Bin Xie", "Rui Shao", "Gongwei Chen", "Kaiwen Zhou", "Yinchuan Li", "Jie Liu", "Min Zhang", "Liqiang Nie"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.acl-long.282", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.acl-long.282/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "5650-5667", "pdf_url": "https://aclanthology.org/2025.acl-long.282.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent", "type": "conference-paper", "url": "https://aclanthology.org/2025.acl-long.282/", "venue": "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "volume": null}} @misc{arxiv_2505_16827, title = {{GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent}}, author = {{Bin Xie} and {Rui Shao} and {Gongwei Chen} and {Kaiwen Zhou} and {Yinchuan Li} and {Jie Liu} and {Min Zhang} and {Liqiang Nie}}, year = {2025}, eprint = {2505.16827v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.16827v1}, note = {First published: 2025-05-22; Recorded arXiv version: v1; Recorded version updated: 2025-05-22T16:01:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.18121", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.18121"}} @misc{arxiv_2505_18121, title = {{ProgRM: Build Better GUI Agents with Progress Rewards}}, author = {{Danyang Zhang} and {Situo Zhang} and {Ziyue Yang} and {Zichen Zhu} and {Zihan Zhao} and {Ruisheng Cao} and {Lu Chen} and {Kai Yu}}, year = {2025}, eprint = {2505.18121v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.18121v1}, note = {First published: 2025-05-23; Recorded arXiv version: v1; Recorded version updated: 2025-05-23T17:23:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.18829", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.18829"}} @misc{arxiv_2505_18829, title = {{LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS}}, author = {{Kai Mei} and {Xi Zhu} and {Hang Gao} and {Shuhang Lin} and {Yongfeng Zhang}}, year = {2025}, eprint = {2505.18829v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.18829v2}, note = {First published: 2025-05-24; Recorded arXiv version: v2; Recorded version updated: 2025-10-31T21:48:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.19095", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.19095"}} @misc{arxiv_2505_19095, title = {{ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World}}, author = {{Runliang Niu} and {Jinglong Ji} and {Yi Chang} and {Qi Wang}}, year = {2025}, eprint = {2505.19095v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.19095v1}, note = {First published: 2025-05-25; Recorded arXiv version: v1; Recorded version updated: 2025-05-25T11:13:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.19897", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.19897"}} @misc{arxiv_2505_19897, title = {{ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows}}, author = {{Qiushi Sun} and {Zhoumianze Liu} and {Chang Ma} and {Zichen Ding} and {Fangzhi Xu} and {Zhangyue Yin} and {Haiteng Zhao} and {Zhenyu Wu} and {Kanzhi Cheng} and {Zhaoyang Liu} and {Jianing Wang} and {Qintong Li} and {Xiangru Tang} and {Tianbao Xie} and {Xiachong Feng} and {Xiang Li} and {Ben Kao} and {Wenhai Wang} and {Biqing Qi} and {Lingpeng Kong} and {Zhiyong Wu}}, year = {2025}, eprint = {2505.19897v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.19897v3}, note = {First published: 2025-05-26; Recorded arXiv version: v3; Recorded version updated: 2026-04-20T16:29:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.20013", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.20013"}} @misc{arxiv_2505_20013, title = {{WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback}}, author = {{Minda Hu} and {Tianqing Fang} and {Jianshu Zhang} and {Junyu Ma} and {Zhisong Zhang} and {Jingyan Zhou} and {Hongming Zhang} and {Haitao Mi} and {Dong Yu} and {Irwin King}}, year = {2025}, eprint = {2505.20013v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.20013v2}, note = {First published: 2025-05-26; Recorded arXiv version: v2; Recorded version updated: 2025-09-18T11:32:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.20660", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.20660"}} @misc{arxiv_2505_20660, title = {{BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism}}, author = {{Qinzhuo Wu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan}}, year = {2025}, eprint = {2505.20660v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.20660v1}, note = {First published: 2025-05-27; Recorded arXiv version: v1; Recorded version updated: 2025-05-27T03:09:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.21279", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.21279"}} @misc{arxiv_2505_21279, title = {{XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State Level}}, author = {{Shaoqing Zhang} and {Kehai Chen} and {Zhuosheng Zhang} and {Rumei Li} and {Rongxiang Weng} and {Yang Xiang} and {Min Zhang}}, year = {2025}, eprint = {2505.21279v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.21279v2}, note = {First published: 2025-05-27; Recorded arXiv version: v2; Recorded version updated: 2025-09-26T09:13:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.21496", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.21496"}} @misc{arxiv_2505_21496, title = {{UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents}}, author = {{Han Xiao} and {Guozhi Wang} and {Yuxiang Chai} and {Zimu Lu} and {Weifeng Lin} and {Hao He} and {Lue Fan} and {Liuyang Bian} and {Rui Hu} and {Liang Liu} and {Shuai Ren} and {Yafei Wen} and {Xiaoxin Chen} and {Aojun Zhou} and {Hongsheng Li}}, year = {2025}, eprint = {2505.21496v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.21496v1}, note = {First published: 2025-05-27; Recorded arXiv version: v1; Recorded version updated: 2025-05-27T17:58:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.21499", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.21499"}} @misc{arxiv_2505_21499, title = {{AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery}}, author = {{Haowei Wang} and {Junjie Wang} and {Xiaojun Jia} and {Rupeng Zhang} and {Mingyang Li} and {Zhe Liu} and {Yang Liu} and {Qing Wang}}, year = {2025}, eprint = {2505.21499v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.21499v1}, note = {First published: 2025-05-27; Recorded arXiv version: v1; Recorded version updated: 2025-05-27T17:59:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.21936", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.21936"}} @misc{arxiv_2505_21936, title = {{RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments}}, author = {{Zeyi Liao} and {Jaylen Jones} and {Linxi Jiang} and {Yuting Ning} and {Eric Fosler-Lussier} and {Yu Su} and {Zhiqiang Lin} and {Huan Sun}}, year = {2025}, eprint = {2505.21936v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.21936v5}, note = {First published: 2025-05-28; Recorded arXiv version: v5; Recorded version updated: 2026-03-01T07:50:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.21964", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.21964"}} @misc{arxiv_2505_21964, title = {{UI-Evol: Automatic Knowledge Evolving for Computer Use Agents}}, author = {{Ziyun Zhang} and {Xinyi Liu} and {Xiaoyi Zhang} and {Jun Wang} and {Gang Chen} and {Yan Lu}}, year = {2025}, eprint = {2505.21964v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.21964v2}, note = {First published: 2025-05-28; Recorded arXiv version: v2; Recorded version updated: 2025-11-03T08:44:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.22942", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.22942"}} @misc{arxiv_2505_22942, title = {{WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning}}, author = {{Yuchen Zhuang} and {Di Jin} and {Jiaao Chen} and {Wenqi Shi} and {Hanrui Wang} and {Chao Zhang}}, year = {2025}, eprint = {2505.22942v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.22942v2}, note = {First published: 2025-05-28; Recorded arXiv version: v2; Recorded version updated: 2025-06-08T07:57:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.23596", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.23596"}} @misc{arxiv_2505_23596, title = {{Agent-SAMA: State-Aware Mobile Assistant}}, author = {{Linqiang Guo} and {Wei Liu} and {Yi Wen Heng} and {Tse-Hsun} and {Chen} and {Yang Wang}}, year = {2025}, eprint = {2505.23596v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.23596v3}, note = {First published: 2025-05-29; Recorded arXiv version: v3; Recorded version updated: 2025-11-19T16:48:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.23762", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.23762"}} @misc{arxiv_2505_23762, title = {{ZeroGUI: Automating Online GUI Learning at Zero Human Cost}}, author = {{Chenyu Yang} and {Shiqian Su} and {Shi Liu} and {Xuan Dong} and {Yue Yu} and {Weijie Su} and {Xuehui Wang} and {Zhaoyang Liu} and {Jinguo Zhu} and {Hao Li} and {Wenhai Wang} and {Yu Qiao} and {Xizhou Zhu} and {Jifeng Dai}}, year = {2025}, eprint = {2505.23762v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.23762v1}, note = {First published: 2025-05-29; Recorded arXiv version: v1; Recorded version updated: 2025-05-29T17:59:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.24838", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.24838"}} @misc{arxiv_2505_24838, title = {{VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video}}, author = {{Brandon Man} and {Ghadi Nehme} and {Md Ferdous Alam} and {Faez Ahmed}}, year = {2025}, eprint = {2505.24838v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24838v2}, note = {First published: 2025-05-30; Recorded arXiv version: v2; Recorded version updated: 2025-11-08T18:27:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2505.24878", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.24878"}} @misc{arxiv_2505_24878, title = {{Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents}}, author = {{Yaxin Luo} and {Zhaoyi Li} and {Jiacheng Liu} and {Jiacheng Cui} and {Xiaohan Zhao} and {Zhiqiang Shen}}, year = {2025}, eprint = {2505.24878v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24878v1}, note = {First published: 2025-05-30; Recorded arXiv version: v1; Recorded version updated: 2025-05-30T17:59:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.00618", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.00618"}} @misc{arxiv_2506_00618, title = {{RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents}}, author = {{Jingyi Yang} and {Shuai Shao} and {Dongrui Liu} and {Jing Shao}}, year = {2025}, eprint = {2506.00618v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.00618v3}, note = {First published: 2025-05-31; Recorded arXiv version: v3; Recorded version updated: 2025-06-20T01:24:06Z.} } % AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2506.01391", "catalog_id": "arxiv:2506.01391", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2506.01391"}, "publication": {"authors": ["Zhong Zhang", "Yaxi Lu", "Yikun Fu", "Yupeng Huo", "Shenzhi Yang", "Yesai Wu", "Han Si (\u53f8\u51fd)", "Xin Cong", "Haotian Chen", "Yankai Lin (\u6797\u884d\u51ef)", "Jie Xie", "Wei Zhou", "Wang Xu", "Yuanheng Zhang", "Zhou Su", "Zhongwu Zhai", "Xiaoming Liu", "Yudong Mei", "Jianming Xu", "Hongyan Tian", "Chongyi Wang", "Chi Chen", "Yuan Yao", "Zhiyuan Liu", "Maosong Sun (\u5b59\u8302\u677e)"], "date_basis": "Explicit publisher citation_publication_date: 2025/11. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 11], "doi": "10.18653/v1/2025.emnlp-demos.12", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.emnlp-demos.12/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "155-180", "pdf_url": "https://aclanthology.org/2025.emnlp-demos.12.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning", "type": "conference-paper", "url": "https://aclanthology.org/2025.emnlp-demos.12/", "venue": "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", "volume": null}} @misc{arxiv_2506_01391, title = {{AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning}}, author = {{Zhong Zhang} and {Yaxi Lu} and {Yikun Fu} and {Yupeng Huo} and {Shenzhi Yang} and {Yesai Wu} and {Han Si} and {Xin Cong} and {Haotian Chen} and {Yankai Lin} and {Jie Xie} and {Wei Zhou} and {Wang Xu} and {Yuanheng Zhang} and {Zhou Su} and {Zhongwu Zhai} and {Xiaoming Liu} and {Yudong Mei} and {Jianming Xu} and {Hongyan Tian} and {Chongyi Wang} and {Chi Chen} and {Yuan Yao} and {Zhiyuan Liu} and {Maosong Sun}}, year = {2025}, eprint = {2506.01391v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.01391v2}, note = {First published: 2025-06-02; Recorded arXiv version: v2; Recorded version updated: 2025-06-17T02:57:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.01616", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.01616"}} @misc{arxiv_2506_01616, title = {{MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments}}, author = {{Xiao Yang} and {Jiawei Chen} and {Jun Luo} and {Zhengwei Fang} and {Yinpeng Dong} and {Hang Su} and {Jun Zhu}}, year = {2025}, eprint = {2506.01616v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.01616v1}, note = {First published: 2025-06-02; Recorded arXiv version: v1; Recorded version updated: 2025-06-02T12:56:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.02456", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.02456"}} @misc{arxiv_2506_02456, title = {{VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents}}, author = {{Tri Cao} and {Bennett Lim} and {Yue Liu} and {Yuan Sui} and {Yuexin Li} and {Shumin Deng} and {Lin Lu} and {Nay Oo} and {Shuicheng Yan} and {Bryan Hooi}}, year = {2025}, eprint = {2506.02456v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.02456v2}, note = {First published: 2025-06-03; Recorded arXiv version: v2; Recorded version updated: 2026-03-01T16:12:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.02539", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.02539"}} @misc{arxiv_2506_02539, title = {{VerificAgent: Domain-Specific Memory Verification for Scalable Oversight of Aligned Computer-Use Agents}}, author = {{Thong Q. Nguyen} and {Shubhang Desai} and {Raja Hasnain Anwar} and {Firoz Shaik} and {Vishwas Suryanarayanan} and {Vishal Chowdhary}}, year = {2025}, eprint = {2506.02539v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.02539v3}, note = {First published: 2025-06-03; Recorded arXiv version: v3; Recorded version updated: 2025-08-07T21:48:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.02839", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.02839"}} @misc{arxiv_2506_02839, title = {{DeepShop: A Benchmark for Deep Research Shopping Agents}}, author = {{Yougang Lyu} and {Xiaoyu Zhang} and {Lingyong Yan} and {Maarten de Rijke} and {Zhaochun Ren} and {Xiuying Chen}}, year = {2025}, eprint = {2506.02839v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.02839v1}, note = {First published: 2025-06-03; Recorded arXiv version: v1; Recorded version updated: 2025-06-03T13:08:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.02865", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.02865"}} @misc{arxiv_2506_02865, title = {{Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights}}, author = {{Mathieu Andreux} and {Breno Baldas Skuk} and {Hamza Benchekroun} and {Emilien Biré} and {Antoine Bonnet} and {Riaz Bordie} and {Nathan Bout} and {Matthias Brunel} and {Pierre-Louis Cedoz} and {Antoine Chassang} and {Mickaël Chen} and {Alexandra D. Constantinou} and {Antoine d'Andigné} and {Hubert de La Jonquière} and {Aurélien Delfosse} and {Ludovic Denoyer} and {Alexis Deprez} and {Augustin Derupti} and {Michael Eickenberg} and {Mathïs Federico} and {Charles Kantor} and {Xavier Koegler} and {Yann Labbé} and {Matthew C. H. Lee} and {Erwan Le Jumeau de Kergaradec} and {Amir Mahla} and {Avshalom Manevich} and {Adrien Maret} and {Charles Masson} and {Rafaël Maurin} and {Arturo Mena} and {Philippe Modard} and {Axel Moyal} and {Axel Nguyen Kerbel} and {Julien Revelle} and {Mats L. Richter} and {María Santos} and {Laurent Sifre} and {Maxime Theillard} and {Marc Thibault} and {Louis Thiry} and {Léo Tronchon} and {Nicolas Usunier} and {Tony Wu}}, year = {2025}, eprint = {2506.02865v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.02865v2}, note = {First published: 2025-06-03; Recorded arXiv version: v2; Recorded version updated: 2025-06-11T09:33:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.03095", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.03095"}} @misc{arxiv_2506_03095, title = {{DPO Learning with LLMs-Judge Signal for Computer Use Agents}}, author = {{Man Luo} and {David Cobbley} and {Xin Su} and {Shachar Rosenman} and {Vasudev Lal} and {Shao-Yen Tseng} and {Phillip Howard}}, year = {2025}, eprint = {2506.03095v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.03095v1}, note = {First published: 2025-06-03; Recorded arXiv version: v1; Recorded version updated: 2025-06-03T17:27:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.03143", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.03143"}} @misc{arxiv_2506_03143, title = {{GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents}}, author = {{Qianhui Wu} and {Kanzhi Cheng} and {Rui Yang} and {Chaoyun Zhang} and {Jianwei Yang} and {Huiqiang Jiang} and {Jian Mu} and {Baolin Peng} and {Bo Qiao} and {Reuben Tan} and {Si Qin} and {Lars Liden} and {Qingwei Lin} and {Huan Zhang} and {Tong Zhang} and {Jianbing Zhang} and {Dongmei Zhang} and {Jianfeng Gao}}, year = {2025}, eprint = {2506.03143v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.03143v1}, note = {First published: 2025-06-03; Recorded arXiv version: v1; Recorded version updated: 2025-06-03T17:59:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.03533", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.03533"}} @misc{arxiv_2506_03533, title = {{Go-Browse: Training Web Agents with Structured Exploration}}, author = {{Apurva Gandhi} and {Graham Neubig}}, year = {2025}, eprint = {2506.03533v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.03533v2}, note = {First published: 2025-06-04; Recorded arXiv version: v2; Recorded version updated: 2026-03-02T22:31:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.04135", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.04135"}} @misc{arxiv_2506_04135, title = {{macOSWorld: A Multilingual Interactive Benchmark for GUI Agents}}, author = {{Pei Yang} and {Hai Ci} and {Mike Zheng Shou}}, year = {2025}, eprint = {2506.04135v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.04135v4}, note = {First published: 2025-06-04; Recorded arXiv version: v4; Recorded version updated: 2025-10-18T12:11:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.04614", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.04614"}} @misc{arxiv_2506_04614, title = {{Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation}}, author = {{Yuyang Wanyan} and {Xi Zhang} and {Haiyang Xu} and {Haowei Liu} and {Junyang Wang} and {Jiabo Ye} and {Yutong Kou} and {Ming Yan} and {Fei Huang} and {Xiaoshan Yang} and {Weiming Dong} and {Changsheng Xu}}, year = {2025}, eprint = {2506.04614v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.04614v2}, note = {First published: 2025-06-05; Recorded arXiv version: v2; Recorded version updated: 2025-11-17T07:48:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.05079", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.05079"}} @misc{arxiv_2506_05079, title = {{Scenario-Guided LLM-based Mobile App GUI Testing}}, author = {{Shengcheng Yu} and {Yuchen Ling} and {Chunrong Fang} and {Quan Zhou} and {Yi Zhao} and {Chunyang Chen} and {Shaomin Zhu} and {Zhenyu Chen}}, year = {2025}, eprint = {2506.05079v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.05079v4}, note = {First published: 2025-06-05; Recorded arXiv version: v4; Recorded version updated: 2026-05-03T08:25:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.07217", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.07217"}} @misc{arxiv_2506_07217, title = {{BIMgent: Towards Autonomous Building Modeling via Computer-use Agents}}, author = {{Zihan Deng} and {Changyu Du} and {Stavros Nousias} and {André Borrmann}}, year = {2025}, eprint = {2506.07217v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.07217v2}, note = {First published: 2025-06-08; Recorded arXiv version: v2; Recorded version updated: 2025-06-30T08:31:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.07385", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.07385"}} @misc{arxiv_2506_07385, title = {{GUIPilot: A Consistency-based Mobile GUI Testing Approach for Detecting Application-specific Bugs}}, author = {{Ruofan Liu} and {Xiwen Teoh} and {Yun Lin} and {Guanjie Chen} and {Ruofei Ren} and {Denys Poshyvanyk} and {Jin Song Dong}}, year = {2025}, eprint = {2506.07385v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.07385v1}, note = {First published: 2025-06-09; Recorded arXiv version: v1; Recorded version updated: 2025-06-09T03:09:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.07672", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.07672"}} @misc{arxiv_2506_07672, title = {{MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents}}, author = {{Yunhe Yan} and {Shihe Wang} and {Jiajun Du} and {Yexuan Yang} and {Yuxuan Shan} and {Qichen Qiu} and {Xianqing Jia} and {Xinge Wang} and {Xin Yuan} and {Xu Han} and {Mao Qin} and {Yinxiao Chen} and {Chen Peng} and {Shangguang Wang} and {Mengwei Xu}}, year = {2025}, eprint = {2506.07672v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.07672v1}, note = {First published: 2025-06-09; Recorded arXiv version: v1; Recorded version updated: 2025-06-09T11:50:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.07976", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.07976"}} @misc{arxiv_2506_07976, title = {{Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction}}, author = {{Junhong Shen} and {Hao Bai} and {Lunjun Zhang} and {Yifei Zhou} and {Amrith Setlur} and {Shengbang Tong} and {Diego Caples} and {Nan Jiang} and {Tong Zhang} and {Ameet Talwalkar} and {Aviral Kumar}}, year = {2025}, eprint = {2506.07976v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.07976v2}, note = {First published: 2025-06-09; Recorded arXiv version: v2; Recorded version updated: 2025-06-10T12:50:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.08012", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.08012"}} @misc{arxiv_2506_08012, title = {{GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior}}, author = {{Penghao Wu} and {Shengnan Ma} and {Bo Wang} and {Jiaheng Yu} and {Lewei Lu} and {Ziwei Liu}}, year = {2025}, eprint = {2506.08012v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.08012v1}, note = {First published: 2025-06-09; Recorded arXiv version: v1; Recorded version updated: 2025-06-09T17:59:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.08136", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.08136"}} @misc{arxiv_2506_08136, title = {{EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments}}, author = {{Zefang Liu} and {Yinzhu Quan}}, year = {2025}, eprint = {2506.08136v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.08136v3}, note = {First published: 2025-06-09; Recorded arXiv version: v3; Recorded version updated: 2026-05-11T08:25:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.08972", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.08972"}} @misc{arxiv_2506_08972, title = {{Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System}}, author = {{Yuan Guo} and {Tingjia Miao} and {Zheng Wu} and {Pengzhou Cheng} and {Ming Zhou} and {Zhuosheng Zhang}}, year = {2025}, eprint = {2506.08972v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.08972v1}, note = {First published: 2025-06-10; Recorded arXiv version: v1; Recorded version updated: 2025-06-10T16:45:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.09373", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.09373"}} @misc{arxiv_2506_09373, title = {{LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization}}, author = {{Jiaqi Tang} and {Yu Xia} and {Yi-Feng Wu} and {Yuwei Hu} and {Yuhui Chen} and {Qing-Guo Chen} and {Xiaogang Xu} and {Xiangyu Wu} and {Hao Lu} and {Yanqing Ma} and {Shiyin Lu} and {Qifeng Chen}}, year = {2025}, eprint = {2506.09373v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.09373v3}, note = {First published: 2025-06-11; Recorded arXiv version: v3; Recorded version updated: 2026-04-21T11:50:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.10387", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.10387"}} @misc{arxiv_2506_10387, title = {{Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills}}, author = {{Yuquan Xie} and {Zaijing Li} and {Rui Shao} and {Gongwei Chen} and {Kaiwen Zhou} and {Yinchuan Li} and {Dongmei Jiang} and {Liqiang Nie}}, year = {2025}, eprint = {2506.10387v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.10387v1}, note = {First published: 2025-06-12; Recorded arXiv version: v1; Recorded version updated: 2025-06-12T06:21:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.11127", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.11127"}} @misc{arxiv_2506_11127, title = {{UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions}}, author = {{Wenkang Han} and {Zhixiong Zeng} and {Jing Huang} and {Shu Jiang} and {Liming Zheng} and {Longrong Yang} and {Haibo Qiu} and {Chang Yao} and {Jingyuan Chen} and {Lin Ma}}, year = {2025}, eprint = {2506.11127v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.11127v3}, note = {First published: 2025-06-10; Recorded arXiv version: v3; Recorded version updated: 2025-11-26T07:48:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.13205", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.13205"}} @misc{arxiv_2506_13205, title = {{Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents}}, author = {{Xuan Wang} and {Siyuan Liang} and {Zhe Liu} and {Yi Yu} and {Aishan Liu} and {Yuliang Lu} and {Xitong Gao} and {Ee-Chien Chang}}, year = {2025}, eprint = {2506.13205v6}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.13205v6}, note = {First published: 2025-06-16; Recorded arXiv version: v6; Recorded version updated: 2025-09-05T14:19:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.14205", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.14205"}} @misc{arxiv_2506_14205, title = {{AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents}}, author = {{Jingxu Xie} and {Dylan Xu} and {Xuandong Zhao} and {Dawn Song}}, year = {2025}, eprint = {2506.14205v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.14205v2}, note = {First published: 2025-06-17; Recorded arXiv version: v2; Recorded version updated: 2026-03-02T00:51:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.14477", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.14477"}} @misc{arxiv_2506_14477, title = {{GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies}}, author = {{Jingqi Yang} and {Zhilong Song} and {Jiawei Chen} and {Mingli Song} and {Sheng Zhou} and {linjun sun} and {Xiaogang Ouyang} and {Chun Chen} and {Can Wang}}, year = {2025}, eprint = {2506.14477v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.14477v1}, note = {First published: 2025-06-17; Recorded arXiv version: v1; Recorded version updated: 2025-06-17T12:50:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.14866", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.14866"}} @misc{arxiv_2506_14866, title = {{OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents}}, author = {{Thomas Kuntz} and {Agatha Duzan} and {Hao Zhao} and {Francesco Croce} and {Zico Kolter} and {Nicolas Flammarion} and {Maksym Andriushchenko}}, year = {2025}, eprint = {2506.14866v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.14866v2}, note = {First published: 2025-06-17; Recorded arXiv version: v2; Recorded version updated: 2025-10-29T10:34:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.15425", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.15425"}} @misc{arxiv_2506_15425, title = {{Understanding GUI Agent Localization Biases through Logit Sharpness}}, author = {{Xingjian Tao} and {Yiwei Wang} and {Yujun Cai} and {Zhicheng Yang} and {Jing Tang}}, year = {2025}, eprint = {2506.15425v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.15425v1}, note = {First published: 2025-06-18; Recorded arXiv version: v1; Recorded version updated: 2025-06-18T12:55:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.15677", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.15677"}} @misc{arxiv_2506_15677, title = {{Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence}}, author = {{Yining Hong} and {Rui Sun} and {Bingxuan Li} and {Xingcheng Yao} and {Maxine Wu} and {Alexander Chien} and {Da Yin} and {Ying Nian Wu} and {Zhecan James Wang} and {Kai-Wei Chang}}, year = {2025}, eprint = {2506.15677v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.15677v3}, note = {First published: 2025-06-18; Recorded arXiv version: v3; Recorded version updated: 2025-07-29T22:40:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.16042", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.16042"}} @misc{arxiv_2506_16042, title = {{OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents}}, author = {{Reyna Abhyankar} and {Qi Qi} and {Yiying Zhang}}, year = {2025}, eprint = {2506.16042v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.16042v2}, note = {First published: 2025-06-19; Recorded arXiv version: v2; Recorded version updated: 2026-05-18T17:55:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.17318", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.17318"}} @misc{arxiv_2506_17318, title = {{Context manipulation attacks : Web agents are susceptible to corrupted memory}}, author = {{Atharv Singh Patlan} and {Ashwin Hebbar} and {Pramod Viswanath} and {Prateek Mittal}}, year = {2025}, eprint = {2506.17318v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.17318v1}, note = {First published: 2025-06-18; Recorded arXiv version: v1; Recorded version updated: 2025-06-18T14:29:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.17913", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.17913"}} @misc{arxiv_2506_17913, title = {{Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents}}, author = {{Jinjie Wei} and {Jiyao Liu} and {Lihao Liu} and {Ming Hu} and {Junzhi Ning} and {Mingcheng Li} and {Weijie Yin} and {Junjun He} and {Xiao Liang} and {Chao Feng} and {Dingkang Yang}}, year = {2025}, eprint = {2506.17913v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.17913v2}, note = {First published: 2025-06-22; Recorded arXiv version: v2; Recorded version updated: 2026-07-21T05:30:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.18158", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.18158"}} @misc{arxiv_2506_18158, title = {{Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation}}, author = {{Xinzge Gao} and {Chuanrui Hu} and {Bin Chen} and {Teng Li}}, year = {2025}, eprint = {2506.18158v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.18158v1}, note = {First published: 2025-06-22; Recorded arXiv version: v1; Recorded version updated: 2025-06-22T20:17:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.20332", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.20332"}} @misc{arxiv_2506_20332, title = {{Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training}}, author = {{Jihao Gu} and {Qihang Ai} and {Yingyao Wang} and {Pi Bu} and {Jingxuan Xing} and {Zekun Zhu} and {Wei Jiang} and {Ziming Wang} and {Yingxiu Zhao} and {Ming-Liang Zhang} and {Jun Song} and {Yuning Jiang} and {Bo Zheng}}, year = {2025}, eprint = {2506.20332v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.20332v4}, note = {First published: 2025-06-25; Recorded arXiv version: v4; Recorded version updated: 2026-04-25T13:54:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2506.23491", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.23491"}} @misc{arxiv_2506_23491, title = {{ZonUI-3B: A Lightweight Vision-Language Model for Cross-Resolution GUI Grounding}}, author = {{ZongHan Hsieh} and {Tzer-Jen Wei} and {ShengJing Yang}}, year = {2025}, eprint = {2506.23491v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.23491v3}, note = {First published: 2025-06-30; Recorded arXiv version: v3; Recorded version updated: 2025-07-18T06:03:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.00008", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.00008"}} @misc{arxiv_2507_00008, title = {{DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning}}, author = {{Hang Wu} and {Hongkai Chen} and {Yujun Cai} and {Chang Liu} and {Qingwen Ye} and {Ming-Hsuan Yang} and {Yiwei Wang}}, year = {2025}, eprint = {2507.00008v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.00008v2}, note = {First published: 2025-06-12; Recorded arXiv version: v2; Recorded version updated: 2025-09-05T17:21:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.00210", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.00210"}} @misc{arxiv_2507_00210, title = {{LineRetriever: Planning-Aware Observation Reduction for Web Agents}}, author = {{Imene Kerboua} and {Sahar Omidi Shayegan} and {Megh Thakkar} and {Xing Han Lù} and {Massimo Caccia} and {Véronique Eglin} and {Alexandre Aussem} and {Jérémy Espinas} and {Alexandre Lacoste}}, year = {2025}, eprint = {2507.00210v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.00210v1}, note = {First published: 2025-06-30; Recorded arXiv version: v1; Recorded version updated: 2025-06-30T19:24:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.00841", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.00841"}} @misc{arxiv_2507_00841, title = {{SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents}}, author = {{Siyuan Liang} and {Tianmeng Fang} and {Zhe Liu} and {Aishan Liu} and {Yan Xiao} and {Jinyuan He} and {Ee-Chien Chang} and {Xiaochun Cao}}, year = {2025}, eprint = {2507.00841v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.00841v1}, note = {First published: 2025-07-01; Recorded arXiv version: v1; Recorded version updated: 2025-07-01T15:10:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.00938", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.00938"}} @misc{arxiv_2507_00938, title = {{WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks}}, author = {{Zihao Sun} and {Zijing Shi} and {Ling Chen}}, year = {2025}, eprint = {2507.00938v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.00938v4}, note = {First published: 2025-07-01; Recorded arXiv version: v4; Recorded version updated: 2026-09-24T12:58:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.03730", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.03730"}} @misc{arxiv_2507_03730, title = {{Less is More: Empowering GUI Agent with Context-Aware Simplification}}, author = {{Gongwei Chen} and {Xurui Zhou} and {Rui Shao} and {Yibo Lyu} and {Kaiwen Zhou} and {Shuai Wang} and {Wentao Li} and {Yinchuan Li} and {Zhongang Qi} and {Liqiang Nie}}, year = {2025}, eprint = {2507.03730v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.03730v1}, note = {First published: 2025-07-04; Recorded arXiv version: v1; Recorded version updated: 2025-07-04T17:37:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.04103", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.04103"}} @misc{arxiv_2507_04103, title = {{How to Train Your LLM Web Agent: A Statistical Diagnosis}}, author = {{Dheeraj Vattikonda} and {Santhoshi Ravichandran} and {Emiliano Penaloza} and {Hadi Nekoei} and {Megh Thakkar} and {Thibault Le Sellier de Chezelles} and {Nicolas Gontier} and {Miguel Muñoz-Mármol} and {Sahar Omidi Shayegan} and {Stefania Raimondo} and {Xue Liu} and {Alexandre Drouin} and {Laurent Charlin} and {Alexandre Piché} and {Alexandre Lacoste} and {Massimo Caccia}}, year = {2025}, eprint = {2507.04103v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.04103v4}, note = {First published: 2025-07-05; Recorded arXiv version: v4; Recorded version updated: 2026-02-13T17:24:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.04227", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.04227"}} @misc{arxiv_2507_04227, title = {{Mobile GUI Agents under Real-world Threats: Are We There Yet?}}, author = {{Guohong Liu} and {Jialei Ye} and {Jiacheng Liu} and {Yuanchun Li} and {Wei Liu} and {Pengzhi Gao} and {Jian Luan} and {Yunxin Liu}}, year = {2025}, eprint = {2507.04227v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.04227v2}, note = {First published: 2025-07-06; Recorded arXiv version: v2; Recorded version updated: 2026-04-14T14:47:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.05445", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.05445"}} @misc{arxiv_2507_05445, title = {{A Systematization of Security Vulnerabilities in Computer Use Agents}}, author = {{Daniel Jones} and {Giorgio Severi} and {Martin Pouliot} and {Gary Lopez} and {Joris de Gruyter} and {Santiago Zanella-Beguelin} and {Justin Song} and {Blake Bullwinkel} and {Pamela Cortez} and {Amanda Minnich}}, year = {2025}, eprint = {2507.05445v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.05445v1}, note = {First published: 2025-07-07; Recorded arXiv version: v1; Recorded version updated: 2025-07-07T19:50:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.05673", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.05673"}} @misc{arxiv_2507_05673, title = {{R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding}}, author = {{Joonhyung Park} and {Peng Tang} and {Sagnik Das} and {Srikar Appalaraju} and {Kunwar Yashraj Singh} and {R. Manmatha} and {Shabnam Ghadar}}, year = {2025}, eprint = {2507.05673v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.05673v1}, note = {First published: 2025-07-08; Recorded arXiv version: v1; Recorded version updated: 2025-07-08T04:56:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.05720", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.05720"}} @misc{arxiv_2507_05720, title = {{MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment}}, author = {{Yucheng Shi} and {Wenhao Yu} and {Zaitang Li} and {Yonglin Wang} and {Hongming Zhang} and {Ninghao Liu} and {Haitao Mi} and {Dong Yu}}, year = {2025}, eprint = {2507.05720v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.05720v1}, note = {First published: 2025-07-08; Recorded arXiv version: v1; Recorded version updated: 2025-07-08T07:07:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.05791", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.05791"}} @misc{arxiv_2507_05791, title = {{GTA1: GUI Test-time Scaling Agent}}, author = {{Yan Yang} and {Dongxu Li} and {Yutong Dai} and {Yuhao Yang} and {Ziyang Luo} and {Zirui Zhao} and {Zhiyuan Hu} and {Junzhe Huang} and {Amrita Saha} and {Zeyuan Chen} and {Ran Xu} and {Liyuan Pan} and {Silvio Savarese} and {Caiming Xiong} and {Junnan Li}}, year = {2025}, eprint = {2507.05791v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.05791v5}, note = {First published: 2025-07-08; Recorded arXiv version: v5; Recorded version updated: 2025-10-03T23:50:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.06134", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.06134"}} @misc{arxiv_2507_06134, title = {{OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety}}, author = {{Sanidhya Vijayvargiya} and {Aditya Bharat Soni} and {Xuhui Zhou} and {Zora Zhiruo Wang} and {Nouha Dziri} and {Graham Neubig} and {Maarten Sap}}, year = {2025}, eprint = {2507.06134v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.06134v2}, note = {First published: 2025-07-08; Recorded arXiv version: v2; Recorded version updated: 2026-02-16T22:34:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.06899", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.06899"}} @misc{arxiv_2507_06899, title = {{VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation}}, author = {{Ziang Ye} and {Yang Zhang} and {Wentao Shi} and {Xiaoyu You} and {Fuli Feng} and {Tat-Seng Chua}}, year = {2025}, eprint = {2507.06899v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.06899v2}, note = {First published: 2025-07-09; Recorded arXiv version: v2; Recorded version updated: 2025-09-24T14:33:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.10610", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.10610"}} @misc{arxiv_2507_10610, title = {{LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents}}, author = {{Zihe Yan} and {Jiaping Gui} and {Zhuosheng Zhang} and {Gongshen Liu}}, year = {2025}, eprint = {2507.10610v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.10610v3}, note = {First published: 2025-07-13; Recorded arXiv version: v3; Recorded version updated: 2026-04-07T11:46:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.12844", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.12844"}} @misc{arxiv_2507_12844, title = {{Machine-Readable Ads: Accessibility and Trust Patterns for AI Web Agents interacting with Online Advertisements}}, author = {{Joel Nitu} and {Heidrun Mühle} and {Andreas Stöckl}}, year = {2025}, eprint = {2507.12844v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.12844v2}, note = {First published: 2025-07-17; Recorded arXiv version: v2; Recorded version updated: 2025-11-12T13:34:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.14293", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.14293"}} @misc{arxiv_2507_14293, title = {{WebGuard: Building a Generalizable Guardrail for Web Agents}}, author = {{Boyuan Zheng} and {Zeyi Liao} and {Scott Salisbury} and {Zeyuan Liu} and {Michael Lin} and {Qinyuan Zheng} and {Zifan Wang} and {Xiang Deng} and {Dawn Song} and {Huan Sun} and {Yu Su}}, year = {2025}, eprint = {2507.14293v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.14293v1}, note = {First published: 2025-07-18; Recorded arXiv version: v1; Recorded version updated: 2025-07-18T18:06:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.14799", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.14799"}} @misc{arxiv_2507_14799, title = {{Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree}}, author = {{Sam Johnson} and {Viet Pham} and {Thai Le}}, year = {2025}, eprint = {2507.14799v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.14799v1}, note = {First published: 2025-07-20; Recorded arXiv version: v1; Recorded version updated: 2025-07-20T03:10:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.15846", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.15846"}} @misc{arxiv_2507_15846, title = {{GUI-G\$\textasciicircum{}2\$: Gaussian Reward Modeling for GUI Grounding}}, author = {{Fei Tang} and {Zhangxuan Gu} and {Zhengxi Lu} and {Xuyang Liu} and {Shuheng Shen} and {Changhua Meng} and {Wen Wang} and {Wenqi Zhang} and {Yongliang Shen} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang}}, year = {2025}, eprint = {2507.15846v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.15846v3}, note = {First published: 2025-07-21; Recorded arXiv version: v3; Recorded version updated: 2025-07-28T16:54:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.16853", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.16853"}} @misc{arxiv_2507_16853, title = {{MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation}}, author = {{Ning Li} and {Xiangmou Qu} and {Jiamu Zhou} and {Jun Wang} and {Muning Wen} and {Kounianhua Du} and {Xingyu Lou} and {Qiuying Peng} and {Jun Wang} and {Weinan Zhang}}, year = {2025}, eprint = {2507.16853v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.16853v1}, note = {First published: 2025-07-21; Recorded arXiv version: v1; Recorded version updated: 2025-07-21T09:37:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.18165", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2507.18165"}} @misc{arxiv_2507_18165, title = {{ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent}}, author = {{Yuheng Zhao} and {Xueli Shu} and {Liwen Fan} and {Lin Gao} and {Yu Zhang} and {Siming Chen}}, year = {2025}, eprint = {2507.18165v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.18165v1}, note = {First published: 2025-07-24; Recorded arXiv version: v1; Recorded version updated: 2025-07-24T08:02:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.19132", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.19132"}} @misc{arxiv_2507_19132, title = {{OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?}}, author = {{Xuetian Chen} and {Yinghao Chen} and {Xinfeng Yuan} and {Zhuo Peng} and {Lu Chen} and {Yuekeng Li} and {Zhoujia Zhang} and {Yingqian Huang} and {Leyan Huang} and {Jiaqing Liang} and {Tianbao Xie} and {Zhiyong Wu} and {Qiushi Sun} and {Biqing Qi} and {Bowen Zhou}}, year = {2025}, eprint = {2507.19132v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.19132v1}, note = {First published: 2025-07-25; Recorded arXiv version: v1; Recorded version updated: 2025-07-25T10:14:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.19478", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.19478"}} @misc{arxiv_2507_19478, title = {{MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents}}, author = {{Xuehui Wang} and {Zhenyu Wu} and {JingJing Xie} and {Zichen Ding} and {Bowen Yang} and {Zehao Li} and {Zhaoyang Liu} and {Qingyun Li} and {Xuan Dong} and {Zhe Chen} and {Weiyun Wang} and {Xiangyu Zhao} and {Jixuan Chen} and {Haodong Duan} and {Tianbao Xie} and {Chenyu Yang} and {Shiqian Su} and {Yue Yu} and {Yuan Huang} and {Yiqian Liu} and {Xiao Zhang} and {Yanting Zhang} and {Xiangyu Yue} and {Weijie Su} and {Xizhou Zhu} and {Wei Shen} and {Jifeng Dai} and {Wenhai Wang}}, year = {2025}, eprint = {2507.19478v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.19478v1}, note = {First published: 2025-07-25; Recorded arXiv version: v1; Recorded version updated: 2025-07-25T17:59:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.21071", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.21071"}} @misc{arxiv_2507_21071, title = {{FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents}}, author = {{Qinglong Yang} and {Haoming Li} and {Haotian Zhao} and {Xiaokai Yan} and {Jingtao Ding} and {Fengli Xu} and {Yong Li}}, year = {2025}, eprint = {2507.21071v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.21071v2}, note = {First published: 2025-06-09; Recorded arXiv version: v2; Recorded version updated: 2026-03-16T09:14:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.21953", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.21953"}} @misc{arxiv_2507_21953, title = {{MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation}}, author = {{Yi Kong} and {Dianxi Shi} and {Guoli Yang} and {Zhang ke-di} and {Chenlin Huang} and {Xiaopeng Li} and {Songchang Jin}}, year = {2025}, eprint = {2507.21953v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.21953v1}, note = {First published: 2025-07-29; Recorded arXiv version: v1; Recorded version updated: 2025-07-29T16:05:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.22025", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.22025"}} @misc{arxiv_2507_22025, title = {{UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding}}, author = {{Shuquan Lian} and {Yuhang Wu} and {Jia Ma} and {Yifan Ding} and {Zihan Song} and {Bingqi Chen} and {Xiawu Zheng} and {Hui Li} and {Rongrong Ji}}, year = {2025}, eprint = {2507.22025v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.22025v4}, note = {First published: 2025-07-29; Recorded arXiv version: v4; Recorded version updated: 2026-04-08T16:03:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.22358", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.22358"}} @misc{arxiv_2507_22358, title = {{Magentic-UI: Towards Human-in-the-loop Agentic Systems}}, author = {{Hussein Mozannar} and {Gagan Bansal} and {Cheng Tan} and {Adam Fourney} and {Victor Dibia} and {Jingya Chen} and {Jack Gerrits} and {Tyler Payne} and {Matheus Kunzler Maldaner} and {Madeleine Grunde-McLaughlin} and {Eric Zhu} and {Griffin Bassman} and {Jacob Alber} and {Peter Chang} and {Ricky Loynd} and {Friederike Niedtner} and {Ece Kamar} and {Maya Murad} and {Rafah Hosn} and {Saleema Amershi}}, year = {2025}, eprint = {2507.22358v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.22358v1}, note = {First published: 2025-07-30; Recorded arXiv version: v1; Recorded version updated: 2025-07-30T03:49:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2507.23779", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.23779"}} @misc{arxiv_2507_23779, title = {{Phi-Ground Tech Report: Advancing Perception in GUI Grounding}}, author = {{Miaosen Zhang} and {Ziqiang Xu} and {Jialiang Zhu} and {Qi Dai} and {Kai Qiu} and {Yifan Yang} and {Chong Luo} and {Tianyi Chen} and {Justin Wagle} and {Tim Franklin} and {Baining Guo}}, year = {2025}, eprint = {2507.23779v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.23779v1}, note = {First published: 2025-07-31; Recorded arXiv version: v1; Recorded version updated: 2025-07-31T17:59:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.01330", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.01330"}} @misc{arxiv_2508_01330, title = {{NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks}}, author = {{Zihan Zheng} and {Tianle Cui} and {Taoran Wang} and {Fengtao Wang} and {Jiahui Pan} and {Lewei He} and {Qianglong Chen}}, year = {2025}, eprint = {2508.01330v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.01330v4}, note = {First published: 2025-08-02; Recorded arXiv version: v4; Recorded version updated: 2026-04-20T02:44:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.01858", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.01858"}} @misc{arxiv_2508_01858, title = {{Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents}}, author = {{Yuhan Guo} and {Cong Guo} and {Aiwen Sun} and {Hongliang He} and {Xinyu Yang} and {Yue Lu} and {Yingji Zhang} and {Xuntao Guo} and {Dong Zhang} and {Jianzhuang Liu} and {Jiang Duan} and {Yijia Xiao} and {Liangjian Wen} and {Hai-Ming Xu} and {Yong Dai}}, year = {2025}, eprint = {2508.01858v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.01858v3}, note = {First published: 2025-08-03; Recorded arXiv version: v3; Recorded version updated: 2026-07-05T06:17:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.02046", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.02046"}} @misc{arxiv_2508_02046, title = {{NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks}}, author = {{Zhihao Luo} and {Wentao Yan} and {Jingyu Gong} and {Min Wang} and {Zhizhong Zhang} and {Xuhong Wang} and {Yuan Xie} and {Xin Tan}}, year = {2025}, eprint = {2508.02046v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.02046v4}, note = {First published: 2025-08-04; Recorded arXiv version: v4; Recorded version updated: 2026-05-02T12:32:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.03700", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.03700"}} @misc{arxiv_2508_03700, title = {{MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning}}, author = {{Liujian Tang} and {Shaokang Dong} and {Yijia Huang} and {Minqi Xiang} and {Hongtao Ruan} and {Bin Wang} and {Shuo Li} and {Zhiheng Xi} and {Zhihui Cao} and {Hailiang Pang} and {Heng Kong} and {He Yang} and {Mingxu Chai} and {Zhilin Gao} and {Xingyu Liu} and {Yingnan Fu} and {Jiaming Liu} and {Xuanjing Huang} and {Yu-Gang Jiang} and {Tao Gui} and {Qi Zhang} and {Kang Wang} and {Yunke Zhang} and {Yuran Wang}}, year = {2025}, eprint = {2508.03700v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.03700v5}, note = {First published: 2025-07-19; Recorded arXiv version: v5; Recorded version updated: 2025-09-11T14:28:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.03923", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.03923"}} @misc{arxiv_2508_03923, title = {{CoAct-1: Computer-using Multi-Agent System with Coding Actions}}, author = {{Linxin Song} and {Yutong Dai} and {Viraj Prabhu} and {Jieyu Zhang} and {Taiwei Shi} and {Li Li} and {Junnan Li} and {Silvio Savarese} and {Zeyuan Chen} and {Jieyu Zhao} and {Ran Xu} and {Caiming Xiong}}, year = {2025}, eprint = {2508.03923v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.03923v3}, note = {First published: 2025-08-05; Recorded arXiv version: v3; Recorded version updated: 2026-02-20T10:14:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.04025", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.04025"}} @misc{arxiv_2508_04025, title = {{Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement}}, author = {{Chao Hao} and {Shuai Wang} and {Kaiwen Zhou}}, year = {2025}, eprint = {2508.04025v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04025v1}, note = {First published: 2025-08-06; Recorded arXiv version: v1; Recorded version updated: 2025-08-06T02:38:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.04037", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.04037"}} @misc{arxiv_2508_04037, title = {{Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent}}, author = {{Yuhao Cheng} and {Liang Tang} and {Shuxian Li} and {Yukang Huo} and {Tiaonan Duan} and {Kaer Huang} and {Yanzhe Jing} and {Yiqiang Yan}}, year = {2025}, eprint = {2508.04037v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04037v2}, note = {First published: 2025-08-06; Recorded arXiv version: v2; Recorded version updated: 2026-01-22T05:22:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.04389", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.04389"}} @misc{arxiv_2508_04389, title = {{GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning}}, author = {{Weitai Kang} and {Bin Lei} and {Gaowen Liu} and {Caiwen Ding} and {Yan Yan}}, year = {2025}, eprint = {2508.04389v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04389v1}, note = {First published: 2025-08-06; Recorded arXiv version: v1; Recorded version updated: 2025-08-06T12:35:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.04412", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.04412"}} @misc{arxiv_2508_04412, title = {{Beyond Pixels: Exploring DOM Downsampling for LLM-Based Web Agents}}, author = {{Thassilo M. Schiepanski} and {Nicholas Piël}}, year = {2025}, eprint = {2508.04412v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04412v4}, note = {First published: 2025-08-06; Recorded arXiv version: v4; Recorded version updated: 2026-08-31T14:39:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.04482", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.04482"}} @misc{arxiv_2508_04482, title = {{OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use}}, author = {{Xueyu Hu} and {Tao Xiong} and {Biao Yi} and {Zishu Wei} and {Ruixuan Xiao} and {Yurun Chen} and {Jiasheng Ye} and {Meiling Tao} and {Xiangxin Zhou} and {Ziyu Zhao} and {Yuhuai Li} and {Shengze Xu} and {Shenzhi Wang} and {Xinchen Xu} and {Shuofei Qiao} and {Zhaokai Wang} and {Kun Kuang} and {Tieyong Zeng} and {Liang Wang} and {Jiwei Li} and {Yuchen Eleanor Jiang} and {Wangchunshu Zhou} and {Guoyin Wang} and {Keting Yin} and {Zhou Zhao} and {Hongxia Yang} and {Fan Wu} and {Shengyu Zhang} and {Fei Wu}}, year = {2025}, eprint = {2508.04482v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04482v1}, note = {First published: 2025-08-06; Recorded arXiv version: v1; Recorded version updated: 2025-08-06T14:33:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.04700", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.04700"}} @misc{arxiv_2508_04700, title = {{SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience}}, author = {{Zeyi Sun} and {Ziyu Liu} and {Yuhang Zang} and {Yuhang Cao} and {Xiaoyi Dong} and {Tong Wu} and {Dahua Lin} and {Jiaqi Wang}}, year = {2025}, eprint = {2508.04700v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04700v2}, note = {First published: 2025-08-06; Recorded arXiv version: v2; Recorded version updated: 2025-08-12T15:11:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.05081", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.05081"}} @misc{arxiv_2508_05081, title = {{Cognitive Duality for Adaptive Web Agents}}, author = {{Jiarun Liu} and {Chunhong Zhang} and {Zheng Hu}}, year = {2025}, eprint = {2508.05081v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.05081v1}, note = {First published: 2025-08-07; Recorded arXiv version: v1; Recorded version updated: 2025-08-07T07:05:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.05615", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.05615"}} @misc{arxiv_2508_05615, title = {{Test-Time Reinforcement Learning for GUI Grounding via Region Consistency}}, author = {{Yong Du} and {Yuchen Yan} and {Fei Tang} and {Zhengxi Lu} and {Chang Zong} and {Weiming Lu} and {Shengpei Jiang} and {Yongliang Shen}}, year = {2025}, eprint = {2508.05615v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.05615v2}, note = {First published: 2025-08-07; Recorded arXiv version: v2; Recorded version updated: 2025-11-13T12:54:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.05731", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.05731"}} @misc{arxiv_2508_05731, title = {{InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization}}, author = {{Yuhang Liu} and {Zeyu Liu} and {Shuanghe Zhu} and {Pengxiang Li} and {Congkai Xie} and {Jiasheng Wang} and {Xavier Hu} and {Xiaotian Han} and {Jianbo Yuan} and {Xinyao Wang} and {Shengyu Zhang} and {Hongxia Yang} and {Fei Wu}}, year = {2025}, eprint = {2508.05731v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.05731v2}, note = {First published: 2025-08-07; Recorded arXiv version: v2; Recorded version updated: 2025-12-08T10:49:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.09057", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.09057"}} @misc{arxiv_2508_09057, title = {{MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions}}, author = {{Zeyu Huang} and {Juyuan Wang} and {Longfeng Chen} and {Boyi Xiao} and {Leng Cai} and {Yawen Zeng} and {Jin Xu}}, year = {2025}, eprint = {2508.09057v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.09057v2}, note = {First published: 2025-08-12; Recorded arXiv version: v2; Recorded version updated: 2025-08-14T16:36:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.09123", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.09123"}} @misc{arxiv_2508_09123, title = {{OpenCUA: Open Foundations for Computer-Use Agents}}, author = {{Xinyuan Wang} and {Bowen Wang} and {Dunjie Lu} and {Junlin Yang} and {Tianbao Xie} and {Junli Wang} and {Jiaqi Deng} and {Xiaole Guo} and {Yiheng Xu} and {Chen Henry Wu} and {Zhennan Shen} and {Zhuokai Li} and {Ryan Li} and {Xiaochuan Li} and {Junda Chen} and {Boyuan Zheng} and {Peihang Li} and {Fangyu Lei} and {Ruisheng Cao} and {Yeqiao Fu} and {Dongchan Shin} and {Martin Shin} and {Jiarui Hu} and {Yuyan Wang} and {Jixuan Chen} and {Yuxiao Ye} and {Danyang Zhang} and {Dikang Du} and {Hao Hu} and {Huarong Chen} and {Zaida Zhou} and {Haotian Yao} and {Ziwei Chen} and {Qizheng Gu} and {Yipu Wang} and {Heng Wang} and {Diyi Yang} and {Victor Zhong} and {Flood Sung} and {Y. Charles} and {Zhilin Yang} and {Tao Yu}}, year = {2025}, eprint = {2508.09123v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.09123v3}, note = {First published: 2025-08-12; Recorded arXiv version: v3; Recorded version updated: 2025-10-04T17:38:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.09241", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.09241"}} @misc{arxiv_2508_09241, title = {{FineState-Bench: A Comprehensive Benchmark for Fine-Grained State Control in GUI Agents}}, author = {{Fengxian Ji} and {Jingpu Yang} and {Zirui Song} and {Yuanxi Wang} and {Zhexuan Cui} and {Yuke Li} and {Qian Jiang} and {Miao Fang} and {Xiuying Chen}}, year = {2025}, eprint = {2508.09241v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.09241v1}, note = {First published: 2025-08-12; Recorded arXiv version: v1; Recorded version updated: 2025-08-12T15:12:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.10833", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.10833"}} @misc{arxiv_2508_10833, title = {{UI-Venus Technical Report: Building High-performance UI Agents with RFT}}, author = {{Zhangxuan Gu} and {Zhengwen Zeng} and {Zhenyu Xu} and {Xingran Zhou} and {Shuheng Shen} and {Yunfei Liu} and {Beitong Zhou} and {Changhua Meng} and {Tianyu Xia} and {Weizhi Chen} and {Yue Wen} and {Jingya Dou} and {Fei Tang} and {Jinzhen Lin} and {Yulin Liu} and {Zhenlin Guo} and {Yichen Gong} and {Heng Jia} and {Changlong Gao} and {Yuan Guo} and {Yong Deng} and {Zhenyu Guo} and {Liang Chen} and {Weiqiang Wang}}, year = {2025}, eprint = {2508.10833v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.10833v2}, note = {First published: 2025-08-14; Recorded arXiv version: v2; Recorded version updated: 2025-08-15T14:49:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.11360", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.11360"}} @misc{arxiv_2508_11360, title = {{CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks}}, author = {{Songqin Nong} and {Xiaoxuan Tang} and {Jingxuan Xu} and {Sheng Zhou} and {Jianfeng Chen} and {Tao Jiang} and {Wenhao Xu}}, year = {2025}, eprint = {2508.11360v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.11360v2}, note = {First published: 2025-08-15; Recorded arXiv version: v2; Recorded version updated: 2026-03-13T11:10:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.13024", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.13024"}} @misc{arxiv_2508_13024, title = {{WebMall -- A Multi-Shop Benchmark for Evaluating Web Agents}}, author = {{Ralph Peeters} and {Aaron Steiner} and {Luca Schwarz} and {Julian Yuya Caspary} and {Christian Bizer}}, year = {2025}, eprint = {2508.13024v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.13024v3}, note = {First published: 2025-08-18; Recorded arXiv version: v3; Recorded version updated: 2026-04-30T09:17:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.13634", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.13634"}} @misc{arxiv_2508_13634, title = {{V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking}}, author = {{Jikai Chen} and {Long Chen} and {Dong Wang} and {Qinglin Su} and {Zhixuan Chu} and {Bingguang Hao} and {Leilei Gan} and {Chenyi Zhuang} and {Jinjie Gu}}, year = {2025}, eprint = {2508.13634v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.13634v3}, note = {First published: 2025-08-19; Recorded arXiv version: v3; Recorded version updated: 2026-01-20T06:39:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.14040", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.14040"}} @misc{arxiv_2508_14040, title = {{ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents}}, author = {{Hanyu Lai} and {Xiao Liu} and {Yanxiao Zhao} and {Han Xu} and {Hanchen Zhang} and {Bohao Jing} and {Yanyu Ren} and {Shuntian Yao} and {Yuxiao Dong} and {Jie Tang}}, year = {2025}, eprint = {2508.14040v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.14040v2}, note = {First published: 2025-08-19; Recorded arXiv version: v2; Recorded version updated: 2025-10-21T05:18:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.14104", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.14104"}} @misc{arxiv_2508_14104, title = {{You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation}}, author = {{Yutong Bian} and {Xianhao Lin} and {Yupeng Xie} and {Tianyang Liu} and {Mingchen Zhuge} and {Siyuan Lu} and {Haoming Tang} and {Jinlin Wang} and {Jiayi Zhang} and {Jiaqi Chen} and {Xiangru Tang} and {Yongxin Ni} and {Sirui Hong} and {Chenglin Wu}}, year = {2025}, eprint = {2508.14104v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.14104v1}, note = {First published: 2025-08-17; Recorded arXiv version: v1; Recorded version updated: 2025-08-17T07:31:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.15144", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.15144"}} @misc{arxiv_2508_15144, title = {{Mobile-Agent-v3: Fundamental Agents for GUI Automation}}, author = {{Jiabo Ye} and {Xi Zhang} and {Haiyang Xu} and {Haowei Liu} and {Junyang Wang} and {Zhaoqing Zhu} and {Ziwei Zheng} and {Feiyu Gao} and {Junjie Cao} and {Zhengxi Lu} and {Jitong Liao} and {Qi Zheng} and {Fei Huang} and {Jingren Zhou} and {Ming Yan}}, year = {2025}, eprint = {2508.15144v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.15144v2}, note = {First published: 2025-08-21; Recorded arXiv version: v2; Recorded version updated: 2025-09-01T05:38:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.15832", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.15832"}} @misc{arxiv_2508_15832, title = {{A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains}}, author = {{Xianren Zhang} and {Shreyas Prasad} and {Di Wang} and {Qiuhai Zeng} and {Suhang Wang} and {Wenbo Yan} and {Mat Hans}}, year = {2025}, eprint = {2508.15832v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.15832v2}, note = {First published: 2025-08-18; Recorded arXiv version: v2; Recorded version updated: 2026-04-21T00:38:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.16987", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.16987"}} @misc{arxiv_2508_16987, title = {{WebSight: A Vision-First Architecture for Robust Web Agents}}, author = {{Tanvir Bhathal} and {Asanshay Gupta}}, year = {2025}, eprint = {2508.16987v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.16987v1}, note = {First published: 2025-08-23; Recorded arXiv version: v1; Recorded version updated: 2025-08-23T11:02:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.18040", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.18040"}} @misc{arxiv_2508_18040, title = {{PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration}}, author = {{Xin Wang} and {Zhiyao Cui} and {Hao Li} and {Ya Zeng} and {Chenxu Wang} and {Ruiqi Song} and {Yihang Chen} and {Kun Shao} and {Qiaosheng Zhang} and {Jinzhuo Liu} and {Siyue Ren} and {Shuyue Hu} and {Zhen Wang}}, year = {2025}, eprint = {2508.18040v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.18040v1}, note = {First published: 2025-08-25; Recorded arXiv version: v1; Recorded version updated: 2025-08-25T13:57:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.18689", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.18689"}} @misc{arxiv_2508_18689, title = {{AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance}}, author = {{Yuyang Zhao} and {Wentao Shi} and {Fuli Feng} and {Xiangnan He}}, year = {2025}, eprint = {2508.18689v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.18689v2}, note = {First published: 2025-08-26; Recorded arXiv version: v2; Recorded version updated: 2025-08-27T04:25:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.19493", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.19493"}} @misc{arxiv_2508_19493, title = {{Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents}}, author = {{Zhixin Lin} and {Jungang Li} and {Shidong Pan} and {Yibo Shi} and {Yue Yao} and {Dongliang Xu}}, year = {2025}, eprint = {2508.19493v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.19493v2}, note = {First published: 2025-08-27; Recorded arXiv version: v2; Recorded version updated: 2025-09-03T07:48:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.19679", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.19679"}} @misc{arxiv_2508_19679, title = {{InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning}}, author = {{Qihang Ai} and {Pi Bu} and {Yue Cao} and {Yingyao Wang} and {Jihao Gu} and {Jingxuan Xing} and {Zekun Zhu} and {Wei Jiang} and {Zhicheng Zheng} and {Jun Song} and {Yuning Jiang}}, year = {2025}, eprint = {2508.19679v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.19679v2}, note = {First published: 2025-08-27; Recorded arXiv version: v2; Recorded version updated: 2026-04-25T13:29:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.20096", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.20096"}} @misc{arxiv_2508_20096, title = {{CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning}}, author = {{Zeyi Sun} and {Yuhang Cao} and {Jianze Liang} and {Qiushi Sun} and {Ziyu Liu} and {Zhixiong Zhang} and {Yuhang Zang} and {Xiaoyi Dong} and {Kai Chen} and {Dahua Lin} and {Jiaqi Wang}}, year = {2025}, eprint = {2508.20096v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.20096v1}, note = {First published: 2025-08-27; Recorded arXiv version: v1; Recorded version updated: 2025-08-27T17:59:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.21456", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.21456"}} @misc{arxiv_2508_21456, title = {{Morae: Proactively Pausing UI Agents for User Choices}}, author = {{Yi-Hao Peng} and {Dingzeyu Li} and {Jeffrey P. Bigham} and {Amy Pavel}}, year = {2025}, eprint = {2508.21456v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.21456v1}, note = {First published: 2025-08-29; Recorded arXiv version: v1; Recorded version updated: 2025-08-29T09:39:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2508.21767", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.21767"}} @misc{arxiv_2508_21767, title = {{UItron: Foundational GUI Agent with Advanced Perception and Planning}}, author = {{Zhixiong Zeng} and {Jing Huang} and {Liming Zheng} and {Wenkang Han} and {Yufeng Zhong} and {Lei Chen} and {Longrong Yang} and {Yingjie Chu} and {Yuzhi He} and {Lin Ma}}, year = {2025}, eprint = {2508.21767v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.21767v1}, note = {First published: 2025-08-29; Recorded arXiv version: v1; Recorded version updated: 2025-08-29T16:40:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.00366", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.00366"}} @misc{arxiv_2509_00366, title = {{KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation}}, author = {{Ziyi Guan} and {Jason Chun Lok Li} and {Zhijian Hou} and {Pingping Zhang} and {Donglai Xu} and {Yuzhi Zhao} and {Mengyang Wu} and {Jinpeng Chen} and {Thanh-Toan Nguyen} and {Pengfei Xian} and {Wenao Ma} and {Shengchao Qin} and {Graziano Chesi} and {Ngai Wong}}, year = {2025}, eprint = {2509.00366v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.00366v1}, note = {First published: 2025-08-30; Recorded arXiv version: v1; Recorded version updated: 2025-08-30T05:32:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.00531", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.00531"}} @misc{arxiv_2509_00531, title = {{MobiAgent: A Systematic Framework for Customizable Mobile Agents}}, author = {{Cheng Zhang} and {Erhu Feng} and {Xi Zhao} and {Yisheng Zhao} and {Wangbo Gong} and {Jiahui Sun} and {Dong Du} and {Zhichao Hua} and {Yubin Xia} and {Haibo Chen}}, year = {2025}, eprint = {2509.00531v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.00531v1}, note = {First published: 2025-08-30; Recorded arXiv version: v1; Recorded version updated: 2025-08-30T15:24:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.01052", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2509.01052"}} @misc{arxiv_2509_01052, title = {{FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games}}, author = {{Jaewoo Ahn} and {Junseo Kim} and {Heeseung Yun} and {Jaehyeon Son} and {Dongmin Park} and {Jaewoong Cho} and {Gunhee Kim}}, year = {2025}, eprint = {2509.01052v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.01052v2}, note = {First published: 2025-09-01; Recorded arXiv version: v2; Recorded version updated: 2025-10-15T10:33:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.01619", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2509.01619"}} @misc{arxiv_2509_01619, title = {{Throttling Web Agents Using Reasoning Gates}}, author = {{Abhinav Kumar} and {Jaechul Roh} and {Ali Naseh} and {Amir Houmansadr} and {Eugene Bagdasarian}}, year = {2025}, eprint = {2509.01619v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.01619v1}, note = {First published: 2025-09-01; Recorded arXiv version: v1; Recorded version updated: 2025-09-01T16:56:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.01720", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.01720"}} @misc{arxiv_2509_01720, title = {{Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control}}, author = {{Georgios Papoudakis} and {Thomas Coste} and {Jianye Hao} and {Jun Wang} and {Kun Shao}}, year = {2025}, eprint = {2509.01720v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.01720v2}, note = {First published: 2025-09-01; Recorded arXiv version: v2; Recorded version updated: 2025-11-13T01:26:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.02322", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.02322"}} @misc{arxiv_2509_02322, title = {{OmniActor: A Generalist GUI and Embodied Agent for 2D\&3D Worlds}}, author = {{Longrong Yang} and {Zhixiong Zeng} and {Yufeng Zhong} and {Jing Huang} and {Liming Zheng} and {Lei Chen} and {Haibo Qiu} and {Zequn Qin} and {Lin Ma} and {Xi Li}}, year = {2025}, eprint = {2509.02322v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.02322v1}, note = {First published: 2025-09-02; Recorded arXiv version: v1; Recorded version updated: 2025-09-02T13:47:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.02444", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.02444"}} @misc{arxiv_2509_02444, title = {{AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent}}, author = {{Jingru Fan} and {Yufan Dang} and {Jingyao Wu} and {Huatao Li} and {Runde Yang} and {Xiyuan Yang} and {Yuheng Wang} and {Chen Qian}}, year = {2025}, eprint = {2509.02444v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.02444v2}, note = {First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-10-17T00:57:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.02544", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.02544"}} @misc{arxiv_2509_02544, title = {{UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning}}, author = {{Haoming Wang} and {Haoyang Zou} and {Huatong Song} and {Jiazhan Feng} and {Junjie Fang} and {Junting Lu} and {Longxiang Liu} and {Qinyu Luo} and {Shihao Liang} and {Shijue Huang} and {Wanjun Zhong} and {Yining Ye} and {Yujia Qin} and {Yuwen Xiong} and {Yuxin Song} and {Zhiyong Wu} and {Aoyan Li} and {Bo Li} and {Chen Dun} and {Chong Liu} and {Daoguang Zan} and {Fuxing Leng} and {Hanbin Wang} and {Hao Yu} and {Haobin Chen} and {Hongyi Guo} and {Jing Su} and {Jingjia Huang} and {Kai Shen} and {Kaiyu Shi} and {Lin Yan} and {Peiyao Zhao} and {Pengfei Liu} and {Qinghao Ye} and {Renjie Zheng} and {Shulin Xin} and {Wayne Xin Zhao} and {Wen Heng} and {Wenhao Huang} and {Wenqian Wang} and {Xiaobo Qin} and {Yi Lin} and {Youbin Wu} and {Zehui Chen} and {Zihao Wang} and {Baoquan Zhong} and {Xinchun Zhang} and {Xujing Li} and {Yuanfan Li} and {Zhongkai Zhao} and {Chengquan Jiang} and {Faming Wu} and {Haotian Zhou} and {Jinlin Pang} and {Li Han} and {Qi Liu} and {Qianli Ma} and {Siyao Liu} and {Songhua Cai} and {Wenqi Fu} and {Xin Liu} and {Yaohui Wang} and {Zhi Zhang} and {Bo Zhou} and {Guoliang Li} and {Jiajun Shi} and {Jiale Yang} and {Jie Tang} and {Li Li} and {Qihua Han} and {Taoran Lu} and {Woyu Lin} and {Xiaokang Tong} and {Xinyao Li} and {Yichi Zhang} and {Yu Miao} and {Zhengxuan Jiang} and {Zili Li} and {Ziyuan Zhao} and {Chenxin Li} and {Dehua Ma} and {Feng Lin} and {Ge Zhang} and {Haihua Yang} and {Hangyu Guo} and {Hongda Zhu} and {Jiaheng Liu} and {Junda Du} and {Kai Cai} and {Kuanye Li} and {Lichen Yuan} and {Meilan Han} and {Minchao Wang} and {Shuyue Guo} and {Tianhao Cheng} and {Xiaobo Ma} and {Xiaojun Xiao} and {Xiaolong Huang} and {Xinjie Chen} and {Yidi Du} and {Yilin Chen} and {Yiwen Wang} and {Zhaojian Li} and {Zhenzhu Yang} and {Zhiyuan Zeng} and {Chaolin Jin} and {Chen Li} and {Hao Chen} and {Haoli Chen} and {Jian Chen} and {Qinghao Zhao} and {Guang Shi}}, year = {2025}, eprint = {2509.02544v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.02544v2}, note = {First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-09-05T14:59:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.03891", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.03891"}} @misc{arxiv_2509_03891, title = {{MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation}}, author = {{Gowen Loo} and {Chang Liu} and {Qinghong Yin} and {Xiang Chen} and {Jiawei Chen} and {Jingyuan Zhang} and {Yu Tian}}, year = {2025}, eprint = {2509.03891v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.03891v1}, note = {First published: 2025-09-04; Recorded arXiv version: v1; Recorded version updated: 2025-09-04T05:22:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.04243", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.04243"}} @misc{arxiv_2509_04243, title = {{Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding}}, author = {{Wanfu Wang} and {Qipeng Huang} and {Guangquan Xue} and {Xiaobo Liang} and {Juntao Li}}, year = {2025}, eprint = {2509.04243v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.04243v1}, note = {First published: 2025-09-04; Recorded arXiv version: v1; Recorded version updated: 2025-09-04T14:17:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.04908", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.04908"}} @misc{arxiv_2509_04908, title = {{SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing}}, author = {{Hongyi Jing} and {Jiafu Chen} and {Chen Rao} and {Ziqiang Dang} and {Jiajie Teng} and {Tianyi Chu} and {Juncheng Mo} and {Shuo Fang} and {Huaizhong Lin} and {Rui Lv} and {Chenguang Ma} and {Lei Zhao}}, year = {2025}, eprint = {2509.04908v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.04908v1}, note = {First published: 2025-09-05; Recorded arXiv version: v1; Recorded version updated: 2025-09-05T08:24:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.06477", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.06477"}} @misc{arxiv_2509_06477, title = {{MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents}}, author = {{Pengxiang Zhao} and {Guangyi Liu} and {YaoZhen Liang} and {Weiqing He} and {Zhengxi Lu} and {WenHao Wang} and {Yuehao Huang} and {Yuxiang Chai} and {Zhaolu Kang} and {Yaxuan Guo} and {Hao Wang} and {Kexin Zhang} and {Liang Liu} and {Yong Liu}}, year = {2025}, eprint = {2509.06477v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.06477v2}, note = {First published: 2025-09-08; Recorded arXiv version: v2; Recorded version updated: 2026-04-15T11:26:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.07553", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.07553"}} @misc{arxiv_2509_07553, title = {{VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents}}, author = {{Zheng Wu} and {Heyuan Huang} and {Xingyu Lou} and {Xiangmou Qu} and {Pengzhou Cheng} and {Zongru Wu} and {Weiwen Liu} and {Weinan Zhang} and {Jun Wang} and {Zhaoxiang Wang} and {Zhuosheng Zhang}}, year = {2025}, eprint = {2509.07553v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.07553v3}, note = {First published: 2025-09-09; Recorded arXiv version: v3; Recorded version updated: 2026-04-03T02:36:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.07764", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.07764"}} @misc{arxiv_2509_07764, title = {{AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents}}, author = {{Haitao Hu} and {Peng Chen} and {Yanpeng Zhao} and {Yuqi Chen}}, year = {2025}, eprint = {2509.07764v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.07764v1}, note = {First published: 2025-09-09; Recorded arXiv version: v1; Recorded version updated: 2025-09-09T13:59:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.10723", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.10723"}} @misc{arxiv_2509_10723, title = {{Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight}}, author = {{Jingyu Tang} and {Chaoran Chen} and {Jiawen Li} and {Zhiping Zhang} and {Bingcan Guo} and {Ibrahim Khalilov} and {Simret Araya Gebreegziabher} and {Bingsheng Yao} and {Dakuo Wang} and {Yanfang Ye} and {Tianshi Li} and {Ziang Xiao} and {Yaxing Yao} and {Toby Jia-Jun Li}}, year = {2025}, eprint = {2509.10723v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.10723v1}, note = {First published: 2025-09-12; Recorded arXiv version: v1; Recorded version updated: 2025-09-12T22:26:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.11250", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.11250"}} @misc{arxiv_2509_11250, title = {{Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments}}, author = {{Yitong Zhang} and {Ximo Li} and {Liyi Cai} and {Jia Li}}, year = {2025}, eprint = {2509.11250v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.11250v3}, note = {First published: 2025-09-14; Recorded arXiv version: v3; Recorded version updated: 2026-08-24T12:04:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.11543", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.11543"}} @misc{arxiv_2509_11543, title = {{UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning}}, author = {{Zhengxi Lu} and {Jiabo Ye} and {Fei Tang} and {Yongliang Shen} and {Haiyang Xu} and {Ziwei Zheng} and {Weiming Lu} and {Ming Yan} and {Fei Huang} and {Jun Xiao} and {Yueting Zhuang}}, year = {2025}, eprint = {2509.11543v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.11543v2}, note = {First published: 2025-09-15; Recorded arXiv version: v2; Recorded version updated: 2025-09-24T15:05:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.11548", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.11548"}} @misc{arxiv_2509_11548, title = {{How Auxiliary Reasoning Unleashes GUI Grounding in VLMs}}, author = {{Weiming Li} and {Yan Shao} and {Jing Yang} and {Yujing Lu} and {Ling Zhong} and {Yuhan Wang} and {Min Yu} and {Tongxiao Ruan} and {Manni Duan}}, year = {2025}, eprint = {2509.11548v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.11548v2}, note = {First published: 2025-09-15; Recorded arXiv version: v2; Recorded version updated: 2026-06-10T01:13:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.11939", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.11939"}} @misc{arxiv_2509_11939, title = {{PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents}}, author = {{Shuning Zhang} and {Yutong Jiang} and {Rongjun Ma} and {Yuting Yang} and {Mingyao Xu} and {Zhixin Huang} and {Xin Yi} and {Hewu Li}}, year = {2025}, eprint = {2509.11939v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.11939v1}, note = {First published: 2025-09-15; Recorded arXiv version: v1; Recorded version updated: 2025-09-15T13:58:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.13615", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.13615"}} @misc{arxiv_2509_13615, title = {{See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles}}, author = {{Zongru Wu} and {Rui Mao} and {Zhiyuan Tian} and {Pengzhou Cheng} and {Tianjie Ju} and {Zheng Wu} and {Lingzhong Dong} and {Haiyue Sheng} and {Zhuosheng Zhang} and {Gongshen Liu}}, year = {2025}, eprint = {2509.13615v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.13615v5}, note = {First published: 2025-09-17; Recorded arXiv version: v5; Recorded version updated: 2026-03-18T08:12:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.13704", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.13704"}} @misc{arxiv_2509_13704, title = {{InfraMind: A Novel Exploration-based GUI Agentic Framework for Mission-critical Industrial Management}}, author = {{Liangtao Lin} and {Zhaomeng Zhu} and {Tianwei Zhang} and {Yonggang Wen}}, year = {2025}, eprint = {2509.13704v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.13704v1}, note = {First published: 2025-09-17; Recorded arXiv version: v1; Recorded version updated: 2025-09-17T05:14:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.14172", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.14172"}} @misc{arxiv_2509_14172, title = {{TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning}}, author = {{Ziyuan Chen} and {Zhenghui Zhao} and {Zhangye Han} and {Miancan Liu} and {Xianhang Ye} and {Yiqing Li} and {Hongbo Min} and {Jinkui Ren} and {Xiantao Zhang} and {Guitao Cao}}, year = {2025}, eprint = {2509.14172v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.14172v2}, note = {First published: 2025-09-17; Recorded arXiv version: v2; Recorded version updated: 2025-09-19T02:13:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.14382", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.14382"}} @misc{arxiv_2509_14382, title = {{Detecting Pipeline Failures through Fine-Grained Analysis of Web Agents}}, author = {{Daniel Röder} and {Akhil Juneja} and {Roland Roller} and {Sven Schmeier}}, year = {2025}, eprint = {2509.14382v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.14382v1}, note = {First published: 2025-09-17; Recorded arXiv version: v1; Recorded version updated: 2025-09-17T19:34:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.15221", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.15221"}} @misc{arxiv_2509_15221, title = {{ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data}}, author = {{Zhaoyang Liu} and {Jingjing Xie} and {Zichen Ding} and {Zehao Li} and {Bowen Yang} and {Zhenyu Wu} and {Xuehui Wang} and {Qiushi Sun} and {Shi Liu} and {Weiyun Wang} and {Shenglong Ye} and {Qingyun Li} and {Xuan Dong} and {Yue Yu} and {Chenyu Lu} and {YunXiang Mo} and {Yao Yan} and {Zeyue Tian} and {Xiao Zhang} and {Yuan Huang} and {Yiqian Liu} and {Weijie Su} and {Gen Luo} and {Xiangyu Yue} and {Biqing Qi} and {Kai Chen} and {Bowen Zhou} and {Yu Qiao} and {Qifeng Chen} and {Wenhai Wang}}, year = {2025}, eprint = {2509.15221v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.15221v2}, note = {First published: 2025-09-18; Recorded arXiv version: v2; Recorded version updated: 2025-09-19T05:29:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.15532", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.15532"}} @misc{arxiv_2509_15532, title = {{GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI Agents}}, author = {{Xianhang Ye} and {Yiqing Li} and {Wei Dai} and {Miancan Liu} and {Ziyuan Chen} and {Zhangye Han} and {Hongbo Min} and {Jinkui Ren} and {Xiantao Zhang} and {Wen Yang} and {Zhi Jin}}, year = {2025}, eprint = {2509.15532v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.15532v1}, note = {First published: 2025-09-19; Recorded arXiv version: v1; Recorded version updated: 2025-09-19T02:34:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.15566", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.15566"}} @misc{arxiv_2509_15566, title = {{BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent}}, author = {{Shaojie Zhang} and {Ruoceng Zhang} and {Pei Fu} and {Shaokang Wang} and {Jiahui Yang} and {Xin Du} and {Shiqi Cui} and {Bin Qin} and {Ying Huang} and {Zhenbo Luo} and {Jian Luan}}, year = {2025}, eprint = {2509.15566v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.15566v4}, note = {First published: 2025-09-19; Recorded arXiv version: v4; Recorded version updated: 2025-10-27T11:34:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.15738", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.15738"}} @misc{arxiv_2509_15738, title = {{GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning}}, author = {{Musen Lin} and {Minghao Liu} and {Taoran Lu} and {Lichen Yuan} and {Yiwei Liu} and {Haonan Xu} and {Yu Miao} and {Yuhao Chao} and {Zhaojian Li}}, year = {2025}, eprint = {2509.15738v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.15738v1}, note = {First published: 2025-09-19; Recorded arXiv version: v1; Recorded version updated: 2025-09-19T08:09:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.17328", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.17328"}} @misc{arxiv_2509_17328, title = {{UIPro: Unleashing Superior Interaction Capability For GUI Agents}}, author = {{Hongxin Li} and {Jingran Su} and {Jingfan Chen} and {Zheng Ju} and {Yuntao Chen} and {Qing Li} and {Zhaoxiang Zhang}}, year = {2025}, eprint = {2509.17328v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.17328v1}, note = {First published: 2025-09-22; Recorded arXiv version: v1; Recorded version updated: 2025-09-22T03:04:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.17917", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.17917"}} @misc{arxiv_2509_17917, title = {{Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent}}, author = {{Junyu Lu} and {Songxin Zhang} and {Zejian Xie} and {Zhuoyang Song} and {Jiaxing Zhang}}, year = {2025}, eprint = {2509.17917v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.17917v1}, note = {First published: 2025-09-22; Recorded arXiv version: v1; Recorded version updated: 2025-09-22T15:40:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.18119", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.18119"}} @misc{arxiv_2509_18119, title = {{MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents}}, author = {{Yifan Xu} and {Xiao Liu} and {Xinghan Liu} and {Jiaqi Fu} and {Hanchen Zhang} and {Bohao Jing} and {Shudan Zhang} and {Yuting Wang} and {Wenyi Zhao} and {Yuxiao Dong}}, year = {2025}, eprint = {2509.18119v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.18119v2}, note = {First published: 2025-09-10; Recorded arXiv version: v2; Recorded version updated: 2025-10-24T17:13:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.20729", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.20729"}} @misc{arxiv_2509_20729, title = {{Robust, Observable, and Evolvable Agentic Systems Engineering: A Principled Framework Validated via the Fairy GUI Agent}}, author = {{Jiazheng Sun} and {Ruimeng Yang} and {Xu Han} and {Jiayang Niu} and {Mingxuan Li} and {Te Yang} and {Yongyong Lu} and {Xin Peng}}, year = {2025}, eprint = {2509.20729v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.20729v2}, note = {First published: 2025-09-25; Recorded arXiv version: v2; Recorded version updated: 2025-12-01T08:01:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.21552", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.21552"}} @misc{arxiv_2509_21552, title = {{Learning GUI Grounding with Spatial Reasoning from Visual Feedback}}, author = {{Yu Zhao} and {Wei-Ning Chen} and {Huseyin Atahan Inan} and {Samuel Kessler} and {Lu Wang} and {Lukas Wutschitz} and {Fangkai Yang} and {Chaoyun Zhang} and {Pasquale Minervini} and {Saravan Rajmohan} and {Robert Sim}}, year = {2025}, eprint = {2509.21552v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.21552v2}, note = {First published: 2025-09-25; Recorded arXiv version: v2; Recorded version updated: 2026-05-25T20:58:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.21782", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.21782"}} @misc{arxiv_2509_21782, title = {{Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety}}, author = {{Junliang Liu} and {Jingyu Xiao} and {Wenxin Tang} and {Zhixian Wang} and {Zipeng Xie} and {Wenxuan Wang} and {Minrui Zhang} and {Shuanghe Yu}}, year = {2025}, eprint = {2509.21782v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.21782v2}, note = {First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-03-04T16:31:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.21823", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.21823"}} @misc{arxiv_2509_21823, title = {{ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration}}, author = {{Gaole Dai} and {Shiqi Jiang} and {Ting Cao} and {Yuqing Yang} and {Yuanchun Li} and {Rui Tan} and {Mo Li} and {Lili Qiu}}, year = {2025}, eprint = {2509.21823v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.21823v2}, note = {First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-04-15T09:19:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.21982", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.21982"}} @misc{arxiv_2509_21982, title = {{RISK: A Framework for GUI Agents in E-commerce Risk Management}}, author = {{Renqi Chen} and {Zeyin Tao} and {Jianming Guo} and {Jingzhe Zhu} and {Yiheng Peng} and {Qingqing Sun} and {Tianyi Zhang} and {Shuai Chen}}, year = {2025}, eprint = {2509.21982v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.21982v2}, note = {First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-04-13T03:14:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.22256", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.22256"}} @misc{arxiv_2509_22256, title = {{Secure and Efficient Access Control for Computer-Use Agents via Context Space}}, author = {{Haochen Gong} and {Chenxiao Li} and {Rui Chang} and {Wenbo Shen}}, year = {2025}, eprint = {2509.22256v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.22256v4}, note = {First published: 2025-09-26; Recorded arXiv version: v4; Recorded version updated: 2026-01-14T06:07:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.23263", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.23263"}} @misc{arxiv_2509_23263, title = {{GUI-PRA: Process Reward Agent for GUI Tasks}}, author = {{Tao Xiong} and {Xavier Hu} and {Yurun Chen} and {Yuhang Liu} and {Changqiao Wu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Shengyu Zhang}}, year = {2025}, eprint = {2509.23263v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.23263v3}, note = {First published: 2025-09-27; Recorded arXiv version: v3; Recorded version updated: 2026-08-30T18:12:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.23866", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.23866"}} @misc{arxiv_2509_23866, title = {{Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation}}, author = {{Pengxiang Li} and {Zechen Hu} and {Zirui Shang} and {Jingrong Wu} and {Yang Liu} and {Hui Liu} and {Zhi Gao} and {Chenrui Shi} and {Bofei Zhang} and {Zihao Zhang} and {Xiaochuan Shi} and {Zedong YU} and {Yuwei Wu} and {Xinxiao Wu} and {Yunde Jia} and {Liuyu Xiang} and {Zhaofeng He} and {Qing Li}}, year = {2025}, eprint = {2509.23866v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.23866v1}, note = {First published: 2025-09-28; Recorded arXiv version: v1; Recorded version updated: 2025-09-28T13:19:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.24133", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.24133"}} @misc{arxiv_2509_24133, title = {{Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding}}, author = {{Zhecheng Li} and {Guoxian Song} and {Yiwei Wang} and {Zhen Xiong} and {Junsong Yuan} and {Yujun Cai}}, year = {2025}, eprint = {2509.24133v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.24133v1}, note = {First published: 2025-09-29; Recorded arXiv version: v1; Recorded version updated: 2025-09-29T00:06:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.24183", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.24183"}} @misc{arxiv_2509_24183, title = {{Retrieval-augmented GUI Agents with Generative Guidelines}}, author = {{Ran Xu} and {Kaixin Ma} and {Wenhao Yu} and {Hongming Zhang} and {Joyce C. Ho} and {Carl Yang} and {Dong Yu}}, year = {2025}, eprint = {2509.24183v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.24183v1}, note = {First published: 2025-09-29; Recorded arXiv version: v1; Recorded version updated: 2025-09-29T02:04:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.25047", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.25047"}} @misc{arxiv_2509_25047, title = {{Scaling Synthetic Task Generation for Agents via Exploration}}, author = {{Ram Ramrakhya} and {Andrew Szot} and {Omar Attia} and {Yuhao Yang} and {Anh Nguyen} and {Bogdan Mazoure} and {Zhe Gan} and {Harsh Agrawal} and {Alexander Toshev}}, year = {2025}, eprint = {2509.25047v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.25047v1}, note = {First published: 2025-09-29; Recorded arXiv version: v1; Recorded version updated: 2025-09-29T17:00:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.25140", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.25140"}} @misc{arxiv_2509_25140, title = {{ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory}}, author = {{Siru Ouyang} and {Jun Yan} and {I-Hung Hsu} and {Yanfei Chen} and {Ke Jiang} and {Zifeng Wang} and {Rujun Han} and {Long T. Le} and {Samira Daruki} and {Xiangru Tang} and {Vishy Tirumalashetty} and {George Lee} and {Mahsan Rofouei} and {Hangfei Lin} and {Jiawei Han} and {Chen-Yu Lee} and {Tomas Pfister}}, year = {2025}, eprint = {2509.25140v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.25140v2}, note = {First published: 2025-09-29; Recorded arXiv version: v2; Recorded version updated: 2026-03-16T20:49:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.26506", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.26506"}} @misc{arxiv_2509_26506, title = {{SCUBA: Salesforce Computer Use Benchmark}}, author = {{Yutong Dai} and {Krithika Ramakrishnan} and {Jing Gu} and {Matthew Fernandez} and {Yanqi Luo} and {Viraj Prabhu} and {Zhenyu Hu} and {Silvio Savarese} and {Caiming Xiong} and {Zeyuan Chen} and {Ran Xu}}, year = {2025}, eprint = {2509.26506v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.26506v1}, note = {First published: 2025-09-30; Recorded arXiv version: v1; Recorded version updated: 2025-09-30T16:48:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2509.26539", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.26539"}} @misc{arxiv_2509_26539, title = {{Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents}}, author = {{Zhen Yang} and {Zi-Yi Dou} and {Di Feng} and {Forrest Huang} and {Anh Nguyen} and {Keen You} and {Omar Attia} and {Yuhao Yang} and {Michael Feng} and {Haotian Zhang} and {Ram Ramrakhya} and {Chao Jia} and {Jeffrey Nichols} and {Alexander Toshev} and {Yinfei Yang} and {Zhe Gan}}, year = {2025}, eprint = {2509.26539v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.26539v1}, note = {First published: 2025-09-30; Recorded arXiv version: v1; Recorded version updated: 2025-09-30T17:13:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.00413", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.00413"}} @misc{arxiv_2510_00413, title = {{PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents}}, author = {{Zikang Liu} and {Junyi Li} and {Wayne Xin Zhao} and {Dawei Gao} and {Yaliang Li} and {Ji-rong Wen}}, year = {2025}, eprint = {2510.00413v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.00413v2}, note = {First published: 2025-10-01; Recorded arXiv version: v2; Recorded version updated: 2025-10-04T15:23:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.00536", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.00536"}} @misc{arxiv_2510_00536, title = {{GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness}}, author = {{Kung-Hsiang Huang} and {Haoyi Qiu} and {Yutong Dai} and {Caiming Xiong} and {Chien-Sheng Wu}}, year = {2025}, eprint = {2510.00536v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.00536v2}, note = {First published: 2025-10-01; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T23:23:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.01354", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.01354"}} @misc{arxiv_2510_01354, title = {{WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents}}, author = {{Yinuo Liu} and {Xilong Wang} and {Ruohan Xu} and {Yuqi Jia} and {Neil Zhenqiang Gong}}, year = {2025}, eprint = {2510.01354v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.01354v2}, note = {First published: 2025-10-01; Recorded arXiv version: v2; Recorded version updated: 2026-09-23T16:44:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.01524", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.01524"}} @misc{arxiv_2510_01524, title = {{WALT: Web Agents that Learn Tools}}, author = {{Viraj Prabhu} and {Yutong Dai} and {Matthew Fernandez} and {Jing Gu} and {Krithika Ramakrishnan} and {Yanqi Luo} and {Silvio Savarese} and {Caiming Xiong} and {Junnan Li} and {Zeyuan Chen} and {Ran Xu}}, year = {2025}, eprint = {2510.01524v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.01524v1}, note = {First published: 2025-10-01; Recorded arXiv version: v1; Recorded version updated: 2025-10-01T23:41:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.01670", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.01670"}} @misc{arxiv_2510_01670, title = {{Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness}}, author = {{Erfan Shayegani} and {Keegan Hines} and {Yue Dong} and {Nael Abu-Ghazaleh} and {Roman Lutz} and {Spencer Whitehead} and {Vidhisha Balachandran} and {Besmira Nushi} and {Vibhav Vineet}}, year = {2025}, eprint = {2510.01670v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.01670v1}, note = {First published: 2025-10-02; Recorded arXiv version: v1; Recorded version updated: 2025-10-02T04:52:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.02250", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.02250"}} @misc{arxiv_2510_02250, title = {{Scaling Agents for Computer Use}}, author = {{Gonzalo Gonzalez-Pumariega} and {Vincent Tu} and {Chih-Lun Lee} and {Jiachen Yang} and {Ang Li} and {Xin Eric Wang}}, year = {2025}, eprint = {2510.02250v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.02250v2}, note = {First published: 2025-10-02; Recorded arXiv version: v2; Recorded version updated: 2026-02-03T23:48:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.02418", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.02418"}} @misc{arxiv_2510_02418, title = {{BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks}}, author = {{Sagnik Anupam} and {Davis Brown} and {Shuo Li} and {Eric Wong} and {Hamed Hassani} and {Osbert Bastani}}, year = {2025}, eprint = {2510.02418v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.02418v2}, note = {First published: 2025-10-02; Recorded arXiv version: v2; Recorded version updated: 2025-10-07T15:12:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.03230", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.03230"}} @misc{arxiv_2510_03230, title = {{Improving GUI Grounding with Explicit Position-to-Coordinate Mapping}}, author = {{Suyuchen Wang} and {Tianyu Zhang} and {Ahmed Masry} and {Christopher Pal} and {Spandana Gella} and {Bang Liu} and {Perouz Taslakian}}, year = {2025}, eprint = {2510.03230v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.03230v1}, note = {First published: 2025-10-03; Recorded arXiv version: v1; Recorded version updated: 2025-10-03T17:59:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.03285", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.03285"}} @misc{arxiv_2510_03285, title = {{WAREX: Web Agent Reliability Evaluation on Existing Benchmarks}}, author = {{Su Kara} and {Fazle Faisal} and {Suman Nath}}, year = {2025}, eprint = {2510.03285v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.03285v1}, note = {First published: 2025-09-28; Recorded arXiv version: v1; Recorded version updated: 2025-09-28T20:51:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.04039", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.04039"}} @misc{arxiv_2510_04039, title = {{\textbackslash{}textsc\textbraceleft{}GUI-Spotlight\textbraceright{}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding}}, author = {{Bin Lei} and {Nuo Xu} and {Ali Payani} and {Mingyi Hong} and {Chunhua Liao} and {Yu Cao} and {Caiwen Ding}}, year = {2025}, eprint = {2510.04039v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.04039v1}, note = {First published: 2025-10-05; Recorded arXiv version: v1; Recorded version updated: 2025-10-05T05:15:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.04373", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.04373"}} @misc{arxiv_2510_04373, title = {{JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation}}, author = {{Hadi Nekoei} and {Aman Jaiswal} and {Patrice Bechard} and {Oleh Shliazhko} and {Orlando Marquez Ayala} and {Mathieu Reymond} and {Massimo Caccia} and {Alexandre Drouin} and {Sarath Chandar} and {Alexandre Lacoste}}, year = {2025}, eprint = {2510.04373v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.04373v2}, note = {First published: 2025-10-05; Recorded arXiv version: v2; Recorded version updated: 2026-02-20T19:34:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.04607", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.04607"}} @misc{arxiv_2510_04607, title = {{From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents}}, author = {{Yuan Wang} and {Mingyu Li} and {Haibo Chen}}, year = {2025}, eprint = {2510.04607v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.04607v2}, note = {First published: 2025-10-06; Recorded arXiv version: v2; Recorded version updated: 2026-03-25T11:29:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.06042", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.06042"}} @misc{arxiv_2510_06042, title = {{Agent+P: Guiding UI Agents via Symbolic Planning}}, author = {{Shang Ma} and {Xusheng Xiao} and {Yanfang Ye}}, year = {2025}, eprint = {2510.06042v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.06042v3}, note = {First published: 2025-10-07; Recorded arXiv version: v3; Recorded version updated: 2026-09-27T17:25:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.07809", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.07809"}} @misc{arxiv_2510_07809, title = {{Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents}}, author = {{Renhua Ding} and {Xiao Yang} and {Zhengwei Fang} and {Jun Luo} and {Kun He} and {Jun Zhu}}, year = {2025}, eprint = {2510.07809v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.07809v4}, note = {First published: 2025-10-09; Recorded arXiv version: v4; Recorded version updated: 2026-04-09T01:41:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.07988", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.07988"}} @misc{arxiv_2510_07988, title = {{ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation}}, author = {{Haitao Jia} and {Ming He} and {Zimo Yin} and {Likang Wu} and {Jianping Fan} and {Jitao Sang}}, year = {2025}, eprint = {2510.07988v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.07988v1}, note = {First published: 2025-10-09; Recorded arXiv version: v1; Recorded version updated: 2025-10-09T09:22:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.09038", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.09038"}} @misc{arxiv_2510_09038, title = {{Auto-scaling Continuous Memory for GUI Agent}}, author = {{Wenyi Wu} and {Kun Zhou} and {Ruoxin Yuan} and {Vivian Yu} and {Stephen Wang} and {Zhiting Hu} and {Biwei Huang}}, year = {2025}, eprint = {2510.09038v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.09038v1}, note = {First published: 2025-10-10; Recorded arXiv version: v1; Recorded version updated: 2025-10-10T06:16:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.09872", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.09872"}} @misc{arxiv_2510_09872, title = {{WARC-Bench: Web Archive Based Benchmark for GUI Subtask Executions}}, author = {{Sanjari Srivastava} and {Gang Li} and {Cheng Chang} and {Rishu Garg} and {Manpreet Kaur} and {Charlene Y. Lee} and {Yuezhang Li} and {Yining Mao} and {Ignacio Cases} and {Yanan Xie} and {Peng Qi}}, year = {2025}, eprint = {2510.09872v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.09872v2}, note = {First published: 2025-10-10; Recorded arXiv version: v2; Recorded version updated: 2026-05-18T22:06:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.10073", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.10073"}} @misc{arxiv_2510_10073, title = {{SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents}}, author = {{Zonghao Ying} and {Yangguang Shao} and {Jianle Gan} and {Gan Xu} and {Wenxin Zhang} and {Quanchen Zou} and {Junzheng Shi} and {Zhenfei Yin} and {Mingchuan Zhang} and {Aishan Liu} and {Xianglong Liu}}, year = {2025}, eprint = {2510.10073v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.10073v2}, note = {First published: 2025-10-11; Recorded arXiv version: v2; Recorded version updated: 2026-04-14T02:53:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.10666", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.10666"}} @misc{arxiv_2510_10666, title = {{BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions}}, author = {{Tao Yu} and {Zhengbo Zhang} and {Zhiheng Lyu} and {Junhao Gong} and {Hongzhu Yi} and {Xinming Wang} and {Yuxuan Zhou} and {Jiabing Yang} and {Ping Nie} and {Yan Huang} and {Wenhu Chen}}, year = {2025}, eprint = {2510.10666v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.10666v2}, note = {First published: 2025-10-12; Recorded arXiv version: v2; Recorded version updated: 2025-10-14T08:54:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.11035", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.11035"}} @misc{arxiv_2510_11035, title = {{SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents}}, author = {{Longjie Guo} and {Chenjie Yuan} and {Mingyuan Zhong} and {Robert Wolfe} and {Ruican Zhong} and {Yue Xu} and {Bingbing Wen} and {Hua Shen} and {Lucy Lu Wang} and {Alexis Hiniker}}, year = {2025}, eprint = {2510.11035v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.11035v2}, note = {First published: 2025-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-02-23T08:31:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.11892", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.11892"}} @misc{arxiv_2510_11892, title = {{R-WoM: Retrieval-augmented World Model For Computer-use Agents}}, author = {{Kai Mei} and {Jiang Guo} and {Shuaichen Chang} and {Mingwen Dong} and {Dongkyu Lee} and {Xing Niu} and {Jiarong Jiang}}, year = {2025}, eprint = {2510.11892v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.11892v2}, note = {First published: 2025-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-03-09T15:25:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.12200", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.12200"}} @misc{arxiv_2510_12200, title = {{HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities}}, author = {{Xiaoxue Ren} and {Penghao Jiang} and {Kaixin Li} and {Zhiyong Huang} and {Xiaoning Du} and {Jiaojiao Jiang} and {Zhenchang Xing} and {Jiamou Sun} and {Terry Yue Zhuo}}, year = {2025}, eprint = {2510.12200v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.12200v1}, note = {First published: 2025-10-14; Recorded arXiv version: v1; Recorded version updated: 2025-10-14T06:52:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.13543", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.13543"}} @misc{arxiv_2510_13543, title = {{In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers}}, author = {{Avihay Cohen}}, year = {2025}, eprint = {2510.13543v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.13543v1}, note = {First published: 2025-10-15; Recorded arXiv version: v1; Recorded version updated: 2025-10-15T13:39:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.14388", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.14388"}} @misc{arxiv_2510_14388, title = {{Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control}}, author = {{Zhe Wu} and {Hongjin Lu} and {Junliang Xing} and {Changhao Zhang} and {Yuxuan Li} and {Yin Zhu} and {Yuhao Yang} and {Yuheng Jing} and {Kai Li} and {Kun Shao} and {Jianye Hao} and {Jun Wang} and {Yuanchun Shi}}, year = {2025}, eprint = {2510.14388v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.14388v2}, note = {First published: 2025-10-16; Recorded arXiv version: v2; Recorded version updated: 2026-02-06T02:04:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.14621", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.14621"}} @misc{arxiv_2510_14621, title = {{ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks}}, author = {{Yuanyi Song} and {Heyuan Huang} and {Qiqiang Lin} and {Yin Zhao} and {Xiangmou Qu} and {Jun Wang} and {Xingyu Lou} and {Weiwen Liu} and {Zhuosheng Zhang} and {Jun Wang} and {Yong Yu} and {Weinan Zhang} and {Zhaoxiang Wang}}, year = {2025}, eprint = {2510.14621v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.14621v1}, note = {First published: 2025-10-16; Recorded arXiv version: v1; Recorded version updated: 2025-10-16T12:30:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.15455", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.15455"}} @misc{arxiv_2510_15455, title = {{CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs}}, author = {{Gucongcong Fan} and {Chaoyue Niu} and {Chengfei Lyu} and {Fan Wu} and {Guihai Chen}}, year = {2025}, eprint = {2510.15455v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.15455v1}, note = {First published: 2025-10-17; Recorded arXiv version: v1; Recorded version updated: 2025-10-17T09:11:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.16051", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.16051"}} @misc{arxiv_2510_16051, title = {{GUIrilla: A Scalable Framework for Automated Desktop UI Exploration}}, author = {{Sofiya Garkot} and {Maksym Shamrai} and {Ivan Synytsia} and {Mariya Hirna}}, year = {2025}, eprint = {2510.16051v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.16051v2}, note = {First published: 2025-10-16; Recorded arXiv version: v2; Recorded version updated: 2026-03-24T14:39:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.16252", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.16252"}} @misc{arxiv_2510_16252, title = {{WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale}}, author = {{Yuxuan Lu} and {Ziyi Wang} and {Jing Huang} and {Hui Liu} and {Jiri Gesi} and {Yan Han} and {Shihan Fu} and {Tianqi Zheng} and {Xianfeng Tang} and {Chen Luo} and {Yisi Sang} and {Jin Lai} and {Dakuo Wang}}, year = {2025}, eprint = {2510.16252v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.16252v2}, note = {First published: 2025-10-17; Recorded arXiv version: v2; Recorded version updated: 2026-05-17T17:26:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.17790", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.17790"}} @misc{arxiv_2510_17790, title = {{UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action}}, author = {{Yuhao Yang} and {Zhen Yang} and {Zi-Yi Dou} and {Anh Nguyen} and {Keen You} and {Omar Attia} and {Andrew Szot} and {Michael Feng} and {Ram Ramrakhya} and {Alexander Toshev} and {Chao Huang} and {Yinfei Yang} and {Zhe Gan}}, year = {2025}, eprint = {2510.17790v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.17790v3}, note = {First published: 2025-10-20; Recorded arXiv version: v3; Recorded version updated: 2026-05-26T11:29:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.18113", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.18113"}} @misc{arxiv_2510_18113, title = {{Investigating the Impact of Dark Patterns on LLM-Based Web Agents}}, author = {{Devin Ersoy} and {Brandon Lee} and {Ananth Shreekumar} and {Arjun Arunasalam} and {Muhammad Ibrahim} and {Antonio Bianchi} and {Z. Berkay Celik}}, year = {2025}, eprint = {2510.18113v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.18113v1}, note = {First published: 2025-10-20; Recorded arXiv version: v1; Recorded version updated: 2025-10-20T21:26:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.18488", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.18488"}} @misc{arxiv_2510_18488, title = {{AndroidControl-Curated: Revealing the True Potential of GUI Agents through Benchmark Purification}}, author = {{Ho Fai Leung} and {Xiaoyan Xi} and {Fei Zuo}}, year = {2025}, eprint = {2510.18488v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.18488v1}, note = {First published: 2025-10-21; Recorded arXiv version: v1; Recorded version updated: 2025-10-21T10:11:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.19205", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.19205"}} @misc{arxiv_2510_19205, title = {{WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation}}, author = {{Yaoyao Qian} and {Yuanli Wang} and {Jinda Zhang} and {Yun Zong} and {Meixu Chen} and {Hanhan Zhou} and {Jindan Huang} and {Yifan Zeng} and {Xinyu Hu} and {Chan Hee Song} and {Danqing Zhang}}, year = {2025}, eprint = {2510.19205v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.19205v1}, note = {First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T03:29:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.19488", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.19488"}} @misc{arxiv_2510_19488, title = {{VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos}}, author = {{Dunjie Lu} and {Yiheng Xu} and {Junli Wang} and {Haoyuan Wu} and {Xinyuan Wang} and {Zekun Wang} and {Junlin Yang} and {Hongjin Su} and {Jixuan Chen} and {Junda Chen} and {Yuchen Mao} and {Jingren Zhou} and {Junyang Lin} and {Binyuan Hui} and {Tao Yu}}, year = {2025}, eprint = {2510.19488v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.19488v1}, note = {First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T11:25:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.19949", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.19949"}} @misc{arxiv_2510_19949, title = {{Surfer 2: The Next Generation of Cross-Platform Computer Use Agents}}, author = {{Mathieu Andreux} and {Märt Bakler} and {Yanael Barbier} and {Hamza Benchekroun} and {Emilien Biré} and {Antoine Bonnet} and {Riaz Bordie} and {Nathan Bout} and {Matthias Brunel} and {Aleix Cambray} and {Pierre-Louis Cedoz} and {Antoine Chassang} and {Gautier Cloix} and {Ethan Connelly} and {Alexandra Constantinou} and {Ramzi De Coster} and {Hubert de la Jonquiere} and {Aurélien Delfosse} and {Maxime Delpit} and {Alexis Deprez} and {Augustin Derupti} and {Mathieu Diaz} and {Shannon D'Souza} and {Julie Dujardin} and {Abai Edmund} and {Michael Eickenberg} and {Armand Fatalot} and {Wissem Felissi} and {Isaac Herring} and {Xavier Koegler} and {Erwan Le Jumeau de Kergaradec} and {Aurélien Lac} and {Maxime Langevin} and {Corentin Lauverjat} and {Antonio Loison} and {Avshalom Manevich} and {Axel Moyal} and {Axel Nguyen Kerbel} and {Marinela Parovic} and {Julien Revelle} and {Guillaume Richard} and {Mats Richter} and {Ronan Riochet} and {María Santos} and {Romain Savidan} and {Laurent Sifre} and {Maxime Theillard} and {Marc Thibault} and {Ivan Valentini} and {Tony Wu} and {Laura Yie} and {Kai Yuan} and {Jevgenij Zubovskij}}, year = {2025}, eprint = {2510.19949v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.19949v2}, note = {First published: 2025-10-22; Recorded arXiv version: v2; Recorded version updated: 2025-10-24T11:52:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.20286", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.20286"}} @misc{arxiv_2510_20286, title = {{UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning}}, author = {{Liangyu Chen} and {Hanzhang Zhou} and {Chenglin Cai} and {Jianan Zhang} and {Panrong Tong} and {Quyu Kong} and {Xu Zhang} and {Chen Liu} and {Yuqi Liu} and {Wenxuan Wang} and {Yue Wang} and {Qin Jin} and {Steven Hoi}}, year = {2025}, eprint = {2510.20286v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.20286v1}, note = {First published: 2025-10-23; Recorded arXiv version: v1; Recorded version updated: 2025-10-23T07:18:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.22009", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.22009"}} @misc{arxiv_2510_22009, title = {{OpenPhone: Mobile Agentic Foundation Models}}, author = {{Yangqin Jiang} and {Chao Huang}}, year = {2025}, eprint = {2510.22009v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.22009v3}, note = {First published: 2025-10-24; Recorded arXiv version: v3; Recorded version updated: 2026-10-05T01:17:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.24168", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.24168"}} @misc{arxiv_2510_24168, title = {{MGA: Memory-Driven GUI Agent for Observation-Centric Interaction}}, author = {{Weihua Cheng} and {Junming Liu} and {Yifei Sun} and {Botian Shi} and {Yirong Chen} and {Ding Wang}}, year = {2025}, eprint = {2510.24168v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.24168v3}, note = {First published: 2025-10-28; Recorded arXiv version: v3; Recorded version updated: 2026-04-14T04:34:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.24411", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.24411"}} @misc{arxiv_2510_24411, title = {{OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows}}, author = {{Qiushi Sun} and {Mukai Li} and {Zhoumianze Liu} and {Zhihui Xie} and {Fangzhi Xu} and {Zhangyue Yin} and {Kanzhi Cheng} and {Zehao Li} and {Zichen Ding} and {Qi Liu} and {Zhiyong Wu} and {Zhuosheng Zhang} and {Ben Kao} and {Lingpeng Kong}}, year = {2025}, eprint = {2510.24411v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.24411v3}, note = {First published: 2025-10-28; Recorded arXiv version: v3; Recorded version updated: 2026-07-26T01:16:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.24563", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.24563"}} @misc{arxiv_2510_24563, title = {{OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents}}, author = {{Hongrui Jia} and {Jitong Liao} and {Xi Zhang} and {Haiyang Xu} and {Tianbao Xie} and {Chaoya Jiang} and {Ming Yan} and {Si Liu} and {Wei Ye} and {Fei Huang}}, year = {2025}, eprint = {2510.24563v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.24563v2}, note = {First published: 2025-10-28; Recorded arXiv version: v2; Recorded version updated: 2025-11-11T04:10:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.27140", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.27140"}} @misc{arxiv_2510_27140, title = {{Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels}}, author = {{Chenghao Du} and {Quanfeng Huang} and {Tingxuan Tang} and {Zihao Wang} and {Adwait Nadkarni} and {Yue Xiao}}, year = {2025}, eprint = {2510.27140v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.27140v3}, note = {First published: 2025-10-31; Recorded arXiv version: v3; Recorded version updated: 2026-07-07T02:18:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.27210", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.27210"}} @misc{arxiv_2510_27210, title = {{GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation}}, author = {{Tao Liu} and {Chongyu Wang} and {Rongjie Li} and {Yingchen Yu} and {Xuming He} and {Bai Song}}, year = {2025}, eprint = {2510.27210v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.27210v1}, note = {First published: 2025-10-31; Recorded arXiv version: v1; Recorded version updated: 2025-10-31T06:10:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2510.27266", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.27266"}} @misc{arxiv_2510_27266, title = {{Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning}}, author = {{Shaojie Zhang} and {Pei Fu} and {Ruoceng Zhang} and {Jiahui Yang} and {Anan Du} and {Xiuwen Xi} and {Shaokang Wang} and {Ying Huang} and {Bin Qin} and {Zhenbo Luo} and {Jian Luan}}, year = {2025}, eprint = {2510.27266v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.27266v2}, note = {First published: 2025-10-31; Recorded arXiv version: v2; Recorded version updated: 2026-05-27T02:32:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.00810", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.00810"}} @misc{arxiv_2511_00810, title = {{GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding}}, author = {{Shijie Zhou} and {Viet Dac Lai} and {Hao Tan} and {Jihyung Kil} and {Wanrong Zhu} and {Changyou Chen} and {Ruiyi Zhang}}, year = {2025}, eprint = {2511.00810v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.00810v4}, note = {First published: 2025-11-02; Recorded arXiv version: v4; Recorded version updated: 2026-06-30T10:43:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.04137", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.04137"}} @misc{arxiv_2511_04137, title = {{Learning from Online Videos at Inference Time for Computer-Use Agents}}, author = {{Yujian Liu} and {Ze Wang} and {Hao Chen} and {Ximeng Sun} and {Xiaodong Yu} and {Jialian Wu} and {Jiang Liu} and {Emad Barsoum} and {Zicheng Liu} and {Shiyu Chang}}, year = {2025}, eprint = {2511.04137v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.04137v1}, note = {First published: 2025-11-06; Recorded arXiv version: v1; Recorded version updated: 2025-11-06T07:29:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.04307", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.04307"}} @misc{arxiv_2511_04307, title = {{GUI-360\$\textasciicircum{}\textbackslash{}circ\$: A Comprehensive Dataset and Benchmark for Computer-Using Agents}}, author = {{Jian Mu} and {Chaoyun Zhang} and {Chiming Ni} and {Lu Wang} and {Bo Qiao} and {Kartik Mathur} and {Qianhui Wu} and {Yuhang Xie} and {Xiaojun Ma} and {Mengyu Zhou} and {Si Qin} and {Liqun Li} and {Yu Kang} and {Minghua Ma} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang}}, year = {2025}, eprint = {2511.04307v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.04307v2}, note = {First published: 2025-11-06; Recorded arXiv version: v2; Recorded version updated: 2025-11-10T12:27:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.06101", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.06101"}} @misc{arxiv_2511_06101, title = {{SynthAgent: Adapting Web Agents with Synthetic Supervision}}, author = {{Zhaoyang Wang} and {Yiming Liang} and {Xuchao Zhang} and {Qianhui Wu} and {Siwei Han} and {Anson Bastos} and {Rujia Wang} and {Chetan Bansal} and {Baolin Peng} and {Jianfeng Gao} and {Saravan Rajmohan} and {Huaxiu Yao}}, year = {2025}, eprint = {2511.06101v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.06101v3}, note = {First published: 2025-11-08; Recorded arXiv version: v3; Recorded version updated: 2026-04-13T06:03:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.06417", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.06417"}} @misc{arxiv_2511_06417, title = {{AUTO-Explorer: Automated Data Collection for GUI Agent}}, author = {{Xiangwu Guo} and {Difei Gao} and {Mike Zheng Shou}}, year = {2025}, eprint = {2511.06417v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.06417v1}, note = {First published: 2025-11-09; Recorded arXiv version: v1; Recorded version updated: 2025-11-09T15:13:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.07332", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.07332"}} @misc{arxiv_2511_07332, title = {{Grounding Computer Use Agents on Human Demonstrations}}, author = {{Aarash Feizi} and {Shravan Nayak} and {Xiangru Jian} and {Kevin Qinghong Lin} and {Kaixin Li} and {Rabiul Awal} and {Xing Han Lù} and {Johan Obando-Ceron} and {Juan A. Rodriguez} and {Nicolas Chapados} and {David Vazquez} and {Adriana Romero-Soriano} and {Reihaneh Rabbany} and {Perouz Taslakian} and {Christopher Pal} and {Spandana Gella} and {Sai Rajeswar}}, year = {2025}, eprint = {2511.07332v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.07332v2}, note = {First published: 2025-11-10; Recorded arXiv version: v2; Recorded version updated: 2026-06-09T21:30:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.09127", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.09127"}} @misc{arxiv_2511_09127, title = {{History-Aware Reasoning for GUI Agents}}, author = {{Ziwei Wang} and {Leyang Yang} and {Xiaoxuan Tang} and {Sheng Zhou} and {Dajun Chen} and {Wei Jiang} and {Yong Li}}, year = {2025}, eprint = {2511.09127v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.09127v1}, note = {First published: 2025-11-12; Recorded arXiv version: v1; Recorded version updated: 2025-11-12T09:06:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.09157", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.09157"}} @misc{arxiv_2511_09157, title = {{ProBench: Benchmarking GUI Agents with Accurate Process Information}}, author = {{Leyang Yang} and {Ziwei Wang} and {Xiaoxuan Tang} and {Sheng Zhou} and {Dajun Chen} and {Wei Jiang} and {Yong Li}}, year = {2025}, eprint = {2511.09157v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.09157v1}, note = {First published: 2025-11-12; Recorded arXiv version: v1; Recorded version updated: 2025-11-12T09:49:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.10705", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.10705"}} @misc{arxiv_2511_10705, title = {{Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents}}, author = {{Yuan Zhao} and {Hualei Zhu} and {Tingyu Jiang} and {Shen Li} and {Xiaohang Xu} and {Hao Henry Wang}}, year = {2025}, eprint = {2511.10705v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.10705v1}, note = {First published: 2025-11-13; Recorded arXiv version: v1; Recorded version updated: 2025-11-13T03:41:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.11672", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.11672"}} @misc{arxiv_2511_11672, title = {{OSGym: Scalable OS Infra for Computer Use Agents}}, author = {{Zengyi Qin} and {Jinyuan Chen} and {Yunze Man} and {Shengcao Cao} and {Ziqi Pang} and {Zhuoyuan Wang} and {Han Fang} and {Ling Zhu} and {Zixin Xie} and {Zibu Wei} and {Tianshu Ran} and {Haoran Geng} and {Ray Pan} and {Qizhen Sun} and {Zachary Bright} and {Yuyang Cai} and {Chongye Yang} and {Jiace Zhao} and {Tianrui Liu} and {Han Cao} and {Yeyang Zhou} and {Rui Wang} and {Song Wang} and {Xiang Ren} and {Bo Zhang} and {Yutong Ban} and {Pieter Abbeel} and {Brian Anthony}}, year = {2025}, eprint = {2511.11672v5}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.11672v5}, note = {First published: 2025-11-11; Recorded arXiv version: v5; Recorded version updated: 2026-04-02T02:42:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.12254", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.12254"}} @misc{arxiv_2511_12254, title = {{Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation}}, author = {{Yuxiang Zhou} and {Jichang Li} and {Yanhao Zhang} and {Haonan Lu} and {Guanbin Li}}, year = {2025}, eprint = {2511.12254v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.12254v3}, note = {First published: 2025-11-15; Recorded arXiv version: v3; Recorded version updated: 2026-03-12T08:45:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.12997", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.12997"}} @misc{arxiv_2511_12997, title = {{WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance}}, author = {{Genglin Liu} and {Shijie Geng} and {Sha Li} and {Hejie Cui} and {Sarah Zhang} and {Xin Liu} and {Tianyi Liu}}, year = {2025}, eprint = {2511.12997v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.12997v2}, note = {First published: 2025-11-17; Recorded arXiv version: v2; Recorded version updated: 2026-07-22T21:19:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.13087", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.13087"}} @misc{arxiv_2511_13087, title = {{MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements}}, author = {{SeokJoo Kwak} and {Jihoon Kim} and {Boyoun Kim} and {Jung Jae Yoon} and {Wooseok Jang} and {Jeonghoon Hong} and {Jaeho Yang} and {Yeong-Dae Kwon}}, year = {2025}, eprint = {2511.13087v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.13087v1}, note = {First published: 2025-11-17; Recorded arXiv version: v1; Recorded version updated: 2025-11-17T07:38:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.13248", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.13248"}} @misc{arxiv_2511_13248, title = {{DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents}}, author = {{Fuyao Zhang} and {Jiaming Zhang} and {Che Wang} and {Xiongtao Sun} and {Yurong Hao} and {Guowei Guan} and {Wenjie Li} and {Longtao Huang} and {Wei Yang Bryan Lim}}, year = {2025}, eprint = {2511.13248v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.13248v1}, note = {First published: 2025-11-17; Recorded arXiv version: v1; Recorded version updated: 2025-11-17T11:08:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.15567", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.15567"}} @misc{arxiv_2511_15567, title = {{Computer-Use Agents as Judges for Generative User Interface}}, author = {{Kevin Qinghong Lin} and {Siyuan Hu} and {Linjie Li} and {Zhengyuan Yang} and {Lijuan Wang} and {Philip Torr} and {Mike Zheng Shou}}, year = {2025}, eprint = {2511.15567v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.15567v1}, note = {First published: 2025-11-19; Recorded arXiv version: v1; Recorded version updated: 2025-11-19T16:00:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.16590", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.16590"}} @misc{arxiv_2511_16590, title = {{D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies}}, author = {{Sen Chen} and {Tong Zhao} and {Yi Bin} and {Fei Ma} and {Wenqi Shao} and {Zheng Wang}}, year = {2025}, eprint = {2511.16590v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.16590v1}, note = {First published: 2025-11-20; Recorded arXiv version: v1; Recorded version updated: 2025-11-20T17:43:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.17131", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.17131"}} @misc{arxiv_2511_17131, title = {{UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational Reliability}}, author = {{Horia Cristescu} and {Charles Park} and {Trong Canh Nguyen} and {Sergiu Talmacel} and {Alexandru-Gabriel Ilie} and {Stefan Adam}}, year = {2025}, eprint = {2511.17131v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.17131v1}, note = {First published: 2025-11-21; Recorded arXiv version: v1; Recorded version updated: 2025-11-21T10:47:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.19477", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.19477"}} @misc{arxiv_2511_19477, title = {{Building Browser Agents: Architecture, Security, and Practical Solutions}}, author = {{Aram Vardanyan}}, year = {2025}, eprint = {2511.19477v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.19477v1}, note = {First published: 2025-11-22; Recorded arXiv version: v1; Recorded version updated: 2025-11-22T12:18:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.19663", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.19663"}} @misc{arxiv_2511_19663, title = {{Fara-7B: An Efficient Agentic Model for Computer Use}}, author = {{Ahmed Awadallah} and {Yash Lara} and {Raghav Magazine} and {Hussein Mozannar} and {Akshay Nambi} and {Yash Pandya} and {Aravind Rajeswaran} and {Corby Rosset} and {Alexey Taymanov} and {Vibhav Vineet} and {Spencer Whitehead} and {Andrew Zhao}}, year = {2025}, eprint = {2511.19663v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.19663v1}, note = {First published: 2025-11-24; Recorded arXiv version: v1; Recorded version updated: 2025-11-24T19:56:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.20067", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.20067"}} @misc{arxiv_2511_20067, title = {{"Are We Done Yet?": A Vision-Based Judge for Autonomous Task Completion of Computer Use Agents}}, author = {{Marta Sumyk} and {Oleksandr Kosovan}}, year = {2025}, eprint = {2511.20067v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.20067v1}, note = {First published: 2025-11-25; Recorded arXiv version: v1; Recorded version updated: 2025-11-25T08:40:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.20766", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.20766"}} @misc{arxiv_2511_20766, title = {{OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability}}, author = {{Karen Ullrich} and {Jingtong Su} and {Claudia Shi} and {Arjun Subramonian} and {Amir Bar} and {Ivan Evtimov} and {Nikolaos Tsilivis} and {Randall Balestriero} and {Julia Kempe} and {Mark Ibrahim}}, year = {2025}, eprint = {2511.20766v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.20766v1}, note = {First published: 2025-11-25; Recorded arXiv version: v1; Recorded version updated: 2025-11-25T19:00:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.21398", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.21398"}} @misc{arxiv_2511_21398, title = {{Prune4Web: DOM Tree Pruning Programming for Web Agent}}, author = {{Jiayuan Zhang} and {Kaiquan Chen} and {Zhihao Lu} and {Enshen Zhou} and {Qian Yu} and {Jing Zhang}}, year = {2025}, eprint = {2511.21398v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.21398v1}, note = {First published: 2025-11-26; Recorded arXiv version: v1; Recorded version updated: 2025-11-26T13:49:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2511.22235", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.22235"}} @misc{arxiv_2511_22235, title = {{Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation}}, author = {{Zehao Deng} and {Tianjie Ju} and {Zheng Wu} and {Zhuosheng Zhang} and {Gongshen Liu}}, year = {2025}, eprint = {2511.22235v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.22235v2}, note = {First published: 2025-11-27; Recorded arXiv version: v2; Recorded version updated: 2026-03-04T12:15:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.00756", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.00756"}} @misc{arxiv_2512_00756, title = {{MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents}}, author = {{Ruihan Chen} and {Qiming Li} and {Xiaocheng Feng} and {Weihong Zhong} and {Xiaoliang Yang} and {Yuxuan Gu} and {Zekun Zhou} and {Yunfei Lu} and {Haoyu Ren} and {Kun Chen} and {Dandan Tu} and {Bing Qin}}, year = {2025}, eprint = {2512.00756v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.00756v2}, note = {First published: 2025-11-30; Recorded arXiv version: v2; Recorded version updated: 2026-04-28T03:32:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.00846", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.00846"}} @misc{arxiv_2512_00846, title = {{AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent}}, author = {{Neeraj Anand} and {Rishabh Jain} and {Sohan Patnaik} and {Balaji Krishnamurthy} and {Mausoom Sarkar}}, year = {2025}, eprint = {2512.00846v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.00846v2}, note = {First published: 2025-11-30; Recorded arXiv version: v2; Recorded version updated: 2025-12-11T18:16:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.01174", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.01174"}} @misc{arxiv_2512_01174, title = {{DrawingBench: Evaluating Spatial Reasoning and UI Interaction Capabilities of Large Language Models through Mouse-Based Drawing Tasks}}, author = {{Hyunjun Kim} and {Sooyoung Ryu}}, year = {2025}, eprint = {2512.01174v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.01174v1}, note = {First published: 2025-12-01; Recorded arXiv version: v1; Recorded version updated: 2025-12-01T01:18:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.01763", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.01763"}} @misc{arxiv_2512_01763, title = {{HiconAgent: History Context-aware Policy Optimization for GUI Agents}}, author = {{Xurui Zhou} and {Gongwei Chen} and {Yuquan Xie} and {Zaijing Li} and {Kaiwen Zhou} and {Shuai Wang} and {Shuo Yang} and {Zhuotao Tian} and {Rui Shao}}, year = {2025}, eprint = {2512.01763v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.01763v2}, note = {First published: 2025-12-01; Recorded arXiv version: v2; Recorded version updated: 2026-03-08T10:18:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.01979", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.01979"}} @misc{arxiv_2512_01979, title = {{Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback}}, author = {{Aiden Yiliu Li} and {Bizhi Yu} and {Daoan Lei} and {Tianhe Ren} and {Shilong Liu}}, year = {2025}, eprint = {2512.01979v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.01979v1}, note = {First published: 2025-12-01; Recorded arXiv version: v1; Recorded version updated: 2025-12-01T18:37:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.02423", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.02423"}} @misc{arxiv_2512_02423, title = {{GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning}}, author = {{Haolong Yan} and {Yeqing Shen} and {Xin Huang} and {Jia Wang} and {Kaijun Tan} and {Zhixuan Liang} and {Hongxin Li} and {Zheng Ge} and {Osamu Yoshie} and {Si Li} and {Xiangyu Zhang} and {Daxin Jiang}}, year = {2025}, eprint = {2512.02423v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.02423v1}, note = {First published: 2025-12-02; Recorded arXiv version: v1; Recorded version updated: 2025-12-02T05:11:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.04105", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.04105"}} @misc{arxiv_2512_04105, title = {{LegalWebAgent: Empowering Access to Justice via LLM-Based Web Agents}}, author = {{Jinzhe Tan} and {Karim Benyekhlef}}, year = {2025}, eprint = {2512.04105v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.04105v1}, note = {First published: 2025-11-28; Recorded arXiv version: v1; Recorded version updated: 2025-11-28T07:26:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.05941", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.05941"}} @misc{arxiv_2512_05941, title = {{Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding}}, author = {{Zhiyuan Jiang} and {Shenghao Xie} and {Wenyi Li} and {Wenqiang Zu} and {Peihang Li} and {Jiahao Qiu} and {Siqi Pei} and {Lei Ma} and {Tiejun Huang} and {Mengdi Wang} and {Shilong Liu}}, year = {2025}, eprint = {2512.05941v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.05941v1}, note = {First published: 2025-12-05; Recorded arXiv version: v1; Recorded version updated: 2025-12-05T18:39:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.07725", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.07725"}} @misc{arxiv_2512_07725, title = {{Privacy Practices of Browser Agents}}, author = {{Alisha Ukani} and {Hamed Haddadi} and {Ali Shahin Shamsabadi} and {Peter Snyder}}, year = {2025}, eprint = {2512.07725v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.07725v1}, note = {First published: 2025-12-08; Recorded arXiv version: v1; Recorded version updated: 2025-12-08T17:16:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.08529", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.08529"}} @misc{arxiv_2512_08529, title = {{MVP: Multiple View Prediction Improves GUI Grounding}}, author = {{Yunzhu Zhang} and {Zeyu Pan} and {Zhengwen Zeng} and {Shuheng Shen} and {Changhua Meng} and {Linchao Zhu}}, year = {2025}, eprint = {2512.08529v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.08529v1}, note = {First published: 2025-12-09; Recorded arXiv version: v1; Recorded version updated: 2025-12-09T12:19:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.09396", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.09396"}} @misc{arxiv_2512_09396, title = {{GAIR: GUI Automation via Information-Joint Reasoning and Group Reflection}}, author = {{Zishu Wei} and {Qixiang Ma} and {Xavier Hu} and {Yuhang Liu} and {Hui Zang} and {Yudong Zhao} and {Tao Wang} and {Shengyu Zhang} and {Fei Wu}}, year = {2025}, eprint = {2512.09396v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.09396v1}, note = {First published: 2025-12-10; Recorded arXiv version: v1; Recorded version updated: 2025-12-10T07:40:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.10371", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.10371"}} @misc{arxiv_2512_10371, title = {{AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management}}, author = {{Shizuo Tian} and {Hao Wen} and {Yuxuan Chen} and {Jiacheng Liu} and {Shanhui Zhao} and {Guohong Liu} and {Ju Ren} and {Yunxin Liu} and {Yuanchun Li}}, year = {2025}, eprint = {2512.10371v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.10371v2}, note = {First published: 2025-12-11; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T09:40:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.10962", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.10962"}} @misc{arxiv_2512_10962, title = {{WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering}}, author = {{Yifei He} and {Pranit Chawla} and {Yaser Souri} and {Subhojit Som} and {Xia Song}}, year = {2025}, eprint = {2512.10962v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.10962v3}, note = {First published: 2025-11-22; Recorded arXiv version: v3; Recorded version updated: 2026-02-04T19:36:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.11611", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.11611"}} @misc{arxiv_2512_11611, title = {{Using GUI Agent for Electronic Design Automation}}, author = {{Chunyi Li} and {Longfei Li} and {Zicheng Zhang} and {Xiaohong Liu} and {Min Tang} and {Weisi Lin} and {Guangtao Zhai}}, year = {2025}, eprint = {2512.11611v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.11611v1}, note = {First published: 2025-12-12; Recorded arXiv version: v1; Recorded version updated: 2025-12-12T14:49:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.12594", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.12594"}} @misc{arxiv_2512_12594, title = {{ceLLMate: Sandboxing Browser AI Agents}}, author = {{Luoxi Meng} and {Henry Feng} and {Ilia Shumailov} and {Earlence Fernandes}}, year = {2025}, eprint = {2512.12594v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.12594v2}, note = {First published: 2025-12-14; Recorded arXiv version: v2; Recorded version updated: 2026-03-04T01:49:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.12634", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.12634"}} @misc{arxiv_2512_12634, title = {{MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents}}, author = {{Youngmin Im} and {Byeongung Jo} and {Jaeyoung Wi} and {Seungwoo Baek} and {Tae Hoon Min} and {Joo Hyung Lee} and {Sangeun Oh} and {Insik Shin} and {Sunjae Lee}}, year = {2025}, eprint = {2512.12634v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.12634v4}, note = {First published: 2025-12-14; Recorded arXiv version: v4; Recorded version updated: 2026-05-31T23:48:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.14014", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.14014"}} @misc{arxiv_2512_14014, title = {{MobileWorldBench: Towards Semantic World Modeling For Mobile Agents}}, author = {{Shufan Li} and {Konstantinos Kallidromitis} and {Akash Gokul} and {Yusuke Kato} and {Kazuki Kozuka} and {Aditya Grover}}, year = {2025}, eprint = {2512.14014v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.14014v2}, note = {First published: 2025-12-16; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T23:06:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.15431", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.15431"}} @misc{arxiv_2512_15431, title = {{Step-GUI Technical Report}}, author = {{Haolong Yan} and {Jia Wang} and {Xin Huang} and {Yeqing Shen} and {Ziyang Meng} and {Zhimin Fan} and {Kaijun Tan} and {Jin Gao} and {Lieyu Shi} and {Mi Yang} and {Shiliang Yang} and {Zhirui Wang} and {Brian Li} and {Kang An} and {Chenyang Li} and {Lei Lei} and {Mengmeng Duan} and {Danxun Liang} and {Guodong Liu} and {Hang Cheng} and {Hao Wu} and {Jie Dong} and {Junhao Huang} and {Mei Chen} and {Renjie Yu} and {Shunshan Li} and {Xu Zhou} and {Yiting Dai} and {Yineng Deng} and {Yingdan Liang} and {Zelin Chen} and {Wen Sun} and {Chengxu Yan} and {Chunqin Xu} and {Dong Li} and {Fengqiong Xiao} and {Guanghao Fan} and {Guopeng Li} and {Guozhen Peng} and {Hongbing Li} and {Hang Li} and {Hongming Chen} and {Jingjing Xie} and {Jianyong Li} and {Jingyang Zhang} and {Jiaju Ren} and {Jiayu Yuan} and {Jianpeng Yin} and {Kai Cao} and {Liang Zhao} and {Liguo Tan} and {Liying Shi} and {Mengqiang Ren} and {Min Xu} and {Manjiao Liu} and {Mao Luo} and {Mingxin Wan} and {Na Wang} and {Nan Wu} and {Ning Wang} and {Peiyao Ma} and {Qingzhou Zhang} and {Qiao Wang} and {Qinlin Zeng} and {Qiong Gao} and {Qiongyao Li} and {Shangwu Zhong} and {Shuli Gao} and {Shaofan Liu} and {Shisi Gao} and {Shuang Luo} and {Xingbin Liu} and {Xiaojia Liu} and {Xiaojie Hou} and {Xin Liu} and {Xuanti Feng} and {Xuedan Cai} and {Xuan Wen} and {Xianwei Zhu} and {Xin Liang} and {Xin Liu} and {Xin Zhou} and {Yifan Sui} and {Yingxiu Zhao} and {Yukang Shi} and {Yunfang Xu} and {Yuqing Zeng} and {Yixun Zhang} and {Zejia Weng} and {Zhonghao Yan} and {Zhiguo Huang} and {Zhuoyu Wang} and {Zihan Yan} and {Zheng Ge} and {Jing Li} and {Yibo Zhu} and {Binxing Jiao} and {Xiangyu Zhang} and {Daxin Jiang}}, year = {2025}, eprint = {2512.15431v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.15431v2}, note = {First published: 2025-12-17; Recorded arXiv version: v2; Recorded version updated: 2025-12-19T17:36:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.16295", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.16295"}} @misc{arxiv_2512_16295, title = {{OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models}}, author = {{Zhenyu Wu} and {Jingjing Xie} and {Zehao Li} and {Bowen Yang} and {Qiushi Sun} and {Zhaoyang Liu} and {Zhoumianze Liu} and {Yu Qiao} and {Xiangyu Yue} and {Zun Wang} and {Zichen Ding}}, year = {2025}, eprint = {2512.16295v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.16295v1}, note = {First published: 2025-12-18; Recorded arXiv version: v1; Recorded version updated: 2025-12-18T08:29:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.16501", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.16501"}} @misc{arxiv_2512_16501, title = {{VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks}}, author = {{Beitong Zhou} and {Zhexiao Huang} and {Yuan Guo} and {Zhangxuan Gu} and {Tianyu Xia} and {Zichen Luo} and {Fei Tang} and {Dehan Kong} and {Yanyi Shang} and {Suling Ou} and {Zhenlin Guo} and {Changhua Meng} and {Shuheng Shen}}, year = {2025}, eprint = {2512.16501v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.16501v1}, note = {First published: 2025-12-18; Recorded arXiv version: v1; Recorded version updated: 2025-12-18T13:09:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.17221", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.17221"}} @misc{arxiv_2512_17221, title = {{DAVE: A VLM Vision Encoder for Document Understanding and Web Agents}}, author = {{Brandon Huang} and {Hang Hua} and {Zhuoran Yu} and {Trevor Darrell} and {Rogerio Feris} and {Roei Herzig}}, year = {2025}, eprint = {2512.17221v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.17221v3}, note = {First published: 2025-12-19; Recorded arXiv version: v3; Recorded version updated: 2025-12-31T17:30:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.19396", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.19396"}} @misc{arxiv_2512_19396, title = {{EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration}}, author = {{Runze Li} and {Yuwen Zhai} and {Bo Xu} and {LiWu Xu} and {Nian Shi} and {Wei Zhang} and {Ran Lin} and {Liang Wang}}, year = {2025}, eprint = {2512.19396v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.19396v3}, note = {First published: 2025-12-22; Recorded arXiv version: v3; Recorded version updated: 2026-04-10T06:20:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.19432", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.19432"}} @misc{arxiv_2512_19432, title = {{MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments}}, author = {{Quyu Kong} and {Xu Zhang} and {Zhenyu Yang} and {Nolan Gao} and {Chen Liu} and {Panrong Tong} and {Chenglin Cai} and {Hanzhang Zhou} and {Jianan Zhang} and {Liangyu Chen} and {Zhidan Liu} and {Steven Hoi} and {Yue Wang}}, year = {2025}, eprint = {2512.19432v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.19432v3}, note = {First published: 2025-12-22; Recorded arXiv version: v3; Recorded version updated: 2025-12-30T07:15:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.21302", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.21302"}} @misc{arxiv_2512_21302, title = {{AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents}}, author = {{Yue Cao} and {Yingyao Wang} and {Pi Bu} and {Jingxuan Xing} and {Wei Jiang} and {Zekun Zhu} and {Junpeng Ma} and {Sashuai Zhou} and {Tong Lu} and {Jun Song} and {Yu Cheng} and {Yuning Jiang} and {Bo Zheng}}, year = {2025}, eprint = {2512.21302v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.21302v1}, note = {First published: 2025-12-24; Recorded arXiv version: v1; Recorded version updated: 2025-12-24T17:40:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.22009", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.22009"}} @misc{arxiv_2512_22009, title = {{iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception}}, author = {{Sarthak Mehrotra} and {Sairam V C Rebbapragada} and {Mani Hemanth Reddy Bonthu} and {Vineeth N Balasubramanian}}, year = {2025}, eprint = {2512.22009v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.22009v1}, note = {First published: 2025-12-26; Recorded arXiv version: v1; Recorded version updated: 2025-12-26T12:09:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.22047", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.22047"}} @misc{arxiv_2512_22047, title = {{MAI-UI Technical Report: Real-World Centric Foundation GUI Agents}}, author = {{Hanzhang Zhou} and {Xu Zhang} and {Panrong Tong} and {Jianan Zhang} and {Liangyu Chen} and {Quyu Kong} and {Chenglin Cai} and {Chen Liu} and {Yue Wang} and {Jingren Zhou} and {Steven Hoi}}, year = {2025}, eprint = {2512.22047v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.22047v1}, note = {First published: 2025-12-26; Recorded arXiv version: v1; Recorded version updated: 2025-12-26T14:51:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.23128", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.23128"}} @misc{arxiv_2512_23128, title = {{It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents}}, author = {{Karolina Korgul} and {Yushi Yang} and {Arkadiusz Drohomirecki} and {Piotr Błaszczyk} and {Will Howard} and {Lukas Aichberger} and {Chris Russell} and {Philip H. S. Torr} and {Adam Mahdi} and {Adel Bibi}}, year = {2025}, eprint = {2512.23128v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.23128v3}, note = {First published: 2025-12-29; Recorded arXiv version: v3; Recorded version updated: 2026-07-02T16:12:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.23647", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.23647"}} @misc{arxiv_2512_23647, title = {{Nested Browser-Use Learning for Agentic Information Seeking}}, author = {{Baixuan Li} and {Jialong Wu} and {Wenbiao Yin} and {Kuan Li} and {Zhongwang Zhang} and {Huifeng Yin} and {Zhengwei Tao} and {Liwen Zhang} and {Pengjun Xie} and {Jingren Zhou} and {Yong Jiang}}, year = {2025}, eprint = {2512.23647v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.23647v1}, note = {First published: 2025-12-29; Recorded arXiv version: v1; Recorded version updated: 2025-12-29T17:59:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2512.24965", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.24965"}} @misc{arxiv_2512_24965, title = {{ShowUI-\$π\$: Flow-based Generative Models as GUI Dexterous Hands}}, author = {{Siyuan Hu} and {Kevin Qinghong Lin} and {Mike Zheng Shou}}, year = {2025}, eprint = {2512.24965v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.24965v1}, note = {First published: 2025-12-31; Recorded arXiv version: v1; Recorded version updated: 2025-12-31T16:51:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.02399", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.02399"}} @misc{arxiv_2601_02399, title = {{ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments}}, author = {{Jiaxin Ai} and {Yukang Feng} and {Fanrui Zhang} and {Jianwen Sun} and {Zizhen Li} and {Chuanhao Li} and {Yifan Chang} and {Wenxiao Wu} and {Ruoxi Wang} and {Mingliang Zhai} and {Kaipeng Zhang}}, year = {2025}, eprint = {2601.02399v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.02399v1}, note = {First published: 2025-12-30; Recorded arXiv version: v1; Recorded version updated: 2025-12-30T01:49:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.02439", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.02439"}} @misc{arxiv_2601_02439, title = {{WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks}}, author = {{Hao Bai} and {Alexey Taymanov} and {Tong Zhang} and {Aviral Kumar} and {Spencer Whitehead}}, year = {2026}, eprint = {2601.02439v6}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.02439v6}, note = {First published: 2026-01-05; Recorded arXiv version: v6; Recorded version updated: 2026-05-02T18:45:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.03928", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.03928"}} @misc{arxiv_2601_03928, title = {{FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection}}, author = {{Mingyu Ouyang} and {Kevin Qinghong Lin} and {Mike Zheng Shou} and {Hwee Tou Ng}}, year = {2026}, eprint = {2601.03928v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.03928v1}, note = {First published: 2026-01-07; Recorded arXiv version: v1; Recorded version updated: 2026-01-07T13:48:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.04035", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.04035"}} @misc{arxiv_2601_04035, title = {{MobileDreamer: Generative Sketch World Model for GUI Agent}}, author = {{Yilin Cao} and {Yufeng Zhong} and {Zhixiong Zeng} and {Siran Dai} and {Liming Zheng} and {Jing Huang} and {Haibo Qiu} and {Peng Shi} and {Wenji Mao}}, year = {2026}, eprint = {2601.04035v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.04035v2}, note = {First published: 2026-01-07; Recorded arXiv version: v2; Recorded version updated: 2026-08-31T13:27:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.04126", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.04126"}} @misc{arxiv_2601_04126, title = {{InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training}}, author = {{Ziyun Zhang} and {Zezhou Wang} and {Xiaoyi Zhang} and {Zongyu Guo} and {Jiahao Li} and {Bin Li} and {Yan Lu}}, year = {2026}, eprint = {2601.04126v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.04126v3}, note = {First published: 2026-01-07; Recorded arXiv version: v3; Recorded version updated: 2026-06-30T13:54:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.04500", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.04500"}} @misc{arxiv_2601_04500, title = {{GUITester: Enabling GUI Agents for Exploratory Defect Discovery}}, author = {{Yifei Gao} and {Jiang Wu} and {Xiaoyi Chen} and {Yifan Yang} and {Zhe Cui} and {Tianyi Ma} and {Jiaming Zhang} and {Jitao Sang}}, year = {2026}, eprint = {2601.04500v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.04500v1}, note = {First published: 2026-01-08; Recorded arXiv version: v1; Recorded version updated: 2026-01-08T02:07:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.05787", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.05787"}} @misc{arxiv_2601_05787, title = {{From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation}}, author = {{Zezhou Wang} and {Ziyun Zhang} and {Xiaoyi Zhang} and {Zhuzhong Qian} and {Yan Lu}}, year = {2026}, eprint = {2601.05787v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.05787v2}, note = {First published: 2026-01-09; Recorded arXiv version: v2; Recorded version updated: 2026-02-10T15:12:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.07181", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.07181"}} @misc{arxiv_2601_07181, title = {{ShowUI-Aloha: Human-Taught GUI Agent}}, author = {{Yichun Zhang} and {Xiangwu Guo} and {Yauhong Goh} and {Jessica Hu} and {Zhiheng Chen} and {Xin Wang} and {Difei Gao} and {Mike Zheng Shou}}, year = {2026}, eprint = {2601.07181v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07181v1}, note = {First published: 2026-01-12; Recorded arXiv version: v1; Recorded version updated: 2026-01-12T04:04:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.07262", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.07262"}} @misc{arxiv_2601_07262, title = {{ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution}}, author = {{Jihong Wang} and {Jiamu Zhou} and {Weiming Zhang} and {Teng Wang} and {Weiwen Liu} and {Zhuosheng Zhang} and {Xingyu Lou} and {Weinan Zhang} and {Huarong Deng} and {Jun Wang}}, year = {2026}, eprint = {2601.07262v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07262v3}, note = {First published: 2026-01-12; Recorded arXiv version: v3; Recorded version updated: 2026-04-23T09:34:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.07263", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.07263"}} @misc{arxiv_2601_07263, title = {{When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent}}, author = {{Xinyi Wu} and {Geng Hong} and {Yueyue Chen} and {MingXuan Liu} and {Feier Jin} and {Xudong Pan} and {Jiarun Dai} and {Baojun Liu}}, year = {2026}, eprint = {2601.07263v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07263v1}, note = {First published: 2026-01-12; Recorded arXiv version: v1; Recorded version updated: 2026-01-12T07:10:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.07779", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.07779"}} @misc{arxiv_2601_07779, title = {{OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent}}, author = {{Bowen Yang} and {Kaiming Jin} and {Zhenyu Wu} and {Zhaoyang Liu} and {Qiushi Sun} and {Zehao Li} and {JingJing Xie} and {Zhoumianze Liu} and {Fangzhi Xu} and {Kanzhi Cheng} and {Qingyun Li} and {Yian Wang} and {Yu Qiao} and {Zun Wang} and {Zichen Ding}}, year = {2026}, eprint = {2601.07779v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07779v1}, note = {First published: 2026-01-12; Recorded arXiv version: v1; Recorded version updated: 2026-01-12T17:55:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.08406", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.08406"}} @misc{arxiv_2601_08406, title = {{WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents}}, author = {{Xinyi Wu} and {Jiagui Chen} and {Geng Hong} and {Jiayi Dong} and {Xudong Pan} and {Jiarun Dai} and {Min Yang}}, year = {2026}, eprint = {2601.08406v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.08406v1}, note = {First published: 2026-01-13; Recorded arXiv version: v1; Recorded version updated: 2026-01-13T10:21:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.08605", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.08605"}} @misc{arxiv_2601_08605, title = {{ExpSeek: Self-Triggered Experience Seeking for Web Agents}}, author = {{Wenyuan Zhang} and {Xinghua Zhang} and {Haiyang Yu} and {Shuaiyi Nie} and {Bingli Wu} and {Juwei Yue} and {Tingwen Liu} and {Yongbin Li}}, year = {2026}, eprint = {2601.08605v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.08605v2}, note = {First published: 2026-01-13; Recorded arXiv version: v2; Recorded version updated: 2026-04-15T14:59:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.09636", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.09636"}} @misc{arxiv_2601_09636, title = {{PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records}}, author = {{Yibo Lyu} and {Gongwei Chen} and {Rui Shao} and {Weili Guan} and {Liqiang Nie}}, year = {2026}, eprint = {2601.09636v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.09636v2}, note = {First published: 2026-01-14; Recorded arXiv version: v2; Recorded version updated: 2026-05-13T02:54:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.09770", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.09770"}} @misc{arxiv_2601_09770, title = {{GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents}}, author = {{Chen Chen} and {Jiawei Shao} and {Dakuan Lu} and {Haoyi Hu} and {Xiangcheng Liu} and {Hantao Yao} and {Wu Liu}}, year = {2026}, eprint = {2601.09770v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.09770v1}, note = {First published: 2026-01-14; Recorded arXiv version: v1; Recorded version updated: 2026-01-14T14:27:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.09923", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.09923"}} @misc{arxiv_2601_09923, title = {{CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents}}, author = {{Hanna Foerster} and {Tom Blanchard} and {Kristina Nikolić} and {Ilia Shumailov} and {Cheng Zhang} and {Robert Mullins} and {Nicolas Papernot} and {Florian Tramèr} and {Yiren Zhao}}, year = {2026}, eprint = {2601.09923v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.09923v3}, note = {First published: 2026-01-14; Recorded arXiv version: v3; Recorded version updated: 2026-06-04T15:38:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.11631", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.11631"}} @misc{arxiv_2601_11631, title = {{Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents}}, author = {{Yurun Song} and {Jiong Yin} and {Rongjunchen Zhang} and {Ian G. Harris}}, year = {2026}, eprint = {2601.11631v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.11631v1}, note = {First published: 2026-01-14; Recorded arXiv version: v1; Recorded version updated: 2026-01-14T03:52:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.12349", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.12349"}} @misc{arxiv_2601_12349, title = {{Mind the Gap: Action Rebinding Attacks against Android GUI Agents}}, author = {{Yi Qian} and {Kunwei Qian} and {Xingbang He} and {Ligeng Chen} and {Jikang Zhang} and {Tiantai Zhang} and {Haiyang Wei} and {Linzhang Wang} and {Hao Wu} and {Bing Mao}}, year = {2026}, eprint = {2601.12349v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.12349v3}, note = {First published: 2026-01-18; Recorded arXiv version: v3; Recorded version updated: 2026-07-15T15:32:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.12822", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.12822"}} @misc{arxiv_2601_12822, title = {{MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction}}, author = {{Wenqi Zhang} and {Yulin Shen} and {Changyue Jiang} and {Jiarun Dai} and {Geng Hong} and {Xudong Pan}}, year = {2026}, eprint = {2601.12822v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.12822v1}, note = {First published: 2026-01-19; Recorded arXiv version: v1; Recorded version updated: 2026-01-19T08:32:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.13060", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.13060"}} @misc{arxiv_2601_13060, title = {{MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux}}, author = {{Zecheng Li} and {Zhihui Cao} and {Wenke Huang} and {Yudong Zhang} and {Keying Qi} and {Rui Wang} and {Zeyu Zheng} and {Jian Zhao} and {Hao Zhu} and {Hengxin Wu} and {Yuran Wang} and {Guitao Fan} and {Guokun Wu} and {Yicong Liu} and {Zhilin Gao} and {Haikun Xu} and {He Yang} and {Minqi Xiang} and {Xingyu Liu} and {Zuojian Wang}}, year = {2026}, eprint = {2601.13060v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.13060v1}, note = {First published: 2026-01-19; Recorded arXiv version: v1; Recorded version updated: 2026-01-19T13:50:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.15876", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.15876"}} @misc{arxiv_2601_15876, title = {{EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience}}, author = {{Taofeng Xue} and {Chong Peng} and {Mianqiu Huang} and {Linsen Guo} and {Tiancheng Han} and {Haozhe Wang} and {Jianing Wang} and {Xiaocheng Zhang} and {Xin Yang} and {Dengchang Zhao} and {Jinrui Ding} and {Xiandi Ma} and {Yuchen Xie} and {Peng Pei} and {Xunliang Cai} and {Xipeng Qiu}}, year = {2026}, eprint = {2601.15876v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.15876v2}, note = {First published: 2026-01-22; Recorded arXiv version: v2; Recorded version updated: 2026-01-23T08:52:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.16356", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.16356"}} @misc{arxiv_2601_16356, title = {{The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes}}, author = {{Simret Araya Gebreegziabher} and {Yukun Yang} and {Charles Chiang} and {Hojun Yoo} and {Chaoran Chen} and {Hyo Jin Do} and {Zahra Ashktorab} and {Werner Geyer} and {Diego Gómez-Zará} and {Toby Jia-Jun Li}}, year = {2026}, eprint = {2601.16356v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.16356v1}, note = {First published: 2026-01-22; Recorded arXiv version: v1; Recorded version updated: 2026-01-22T22:42:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.17418", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.17418"}} @misc{arxiv_2601_17418, title = {{GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge Graph}}, author = {{Mingxian Yu} and {Siqi Luo} and {Xu Chen}}, year = {2026}, eprint = {2601.17418v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.17418v1}, note = {First published: 2026-01-24; Recorded arXiv version: v1; Recorded version updated: 2026-01-24T11:35:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.17722", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.17722"}} @misc{arxiv_2601_17722, title = {{EntWorld: A Holistic Environment and Benchmark for Verifiable Enterprise GUI Agents}}, author = {{Ying Mo} and {Yu Bai} and {Dapeng Sun} and {Yuqian Shi} and {Yukai Miao} and {Li Chen} and {Dan Li}}, year = {2026}, eprint = {2601.17722v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.17722v1}, note = {First published: 2026-01-25; Recorded arXiv version: v1; Recorded version updated: 2026-01-25T06:58:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.18092", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2601.18092"}} @misc{arxiv_2601_18092, title = {{From Struggle to Success: Context-Aware Guidance for Screen Reader Users in Computer Use}}, author = {{Nan Chen} and {Jing Lu} and {Zilong Wang} and {Luna K. Qiu} and {Siming Chen} and {Yuqing Yang}}, year = {2026}, eprint = {2601.18092v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.18092v1}, note = {First published: 2026-01-26; Recorded arXiv version: v1; Recorded version updated: 2026-01-26T03:02:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.18197", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.18197"}} @misc{arxiv_2601_18197, title = {{GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models}}, author = {{Shaokang Wang} and {Pei Fu} and {Ruoceng Zhang} and {Shaojie Zhang} and {Xiuwen Xi} and {Jiahui Yang} and {Bin Qin} and {Ying Huang} and {Zhenbo Luo} and {Jian Luan}}, year = {2026}, eprint = {2601.18197v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.18197v2}, note = {First published: 2026-01-26; Recorded arXiv version: v2; Recorded version updated: 2026-06-26T07:19:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.18305", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.18305"}} @misc{arxiv_2601_18305, title = {{SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis}}, author = {{Xuan Wang} and {Siyuan Su} and {Quantong Fu} and {Yongxiang Hu} and {Yangfan Zhou}}, year = {2026}, eprint = {2601.18305v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.18305v2}, note = {First published: 2026-01-26; Recorded arXiv version: v2; Recorded version updated: 2026-08-20T07:50:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.18842", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.18842"}} @misc{arxiv_2601_18842, title = {{GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents}}, author = {{Yanxi Wang} and {Zhiling Zhang} and {Wenbo Zhou} and {Weiming Zhang} and {Jie Zhang} and {Qiannan Zhu} and {Yu Shi} and {Shuxin Zheng} and {Jiyan He}}, year = {2026}, eprint = {2601.18842v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.18842v3}, note = {First published: 2026-01-26; Recorded arXiv version: v3; Recorded version updated: 2026-05-13T07:11:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.19199", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.19199"}} @misc{arxiv_2601_19199, title = {{MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution}}, author = {{Libo Sun} and {Jiwen Zhang} and {Siyuan Wang} and {Zhongyu Wei}}, year = {2026}, eprint = {2601.19199v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.19199v2}, note = {First published: 2026-01-27; Recorded arXiv version: v2; Recorded version updated: 2026-01-31T15:17:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.19306", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.19306"}} @misc{arxiv_2601_19306, title = {{Curiosity Driven Knowledge Retrieval for Mobile Agents}}, author = {{Sijia Li} and {Xiaoyu Tan} and {Shahir Ali} and {Niels Schmidt} and {Gengchen Ma} and {Xihe Qiu}}, year = {2026}, eprint = {2601.19306v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.19306v1}, note = {First published: 2026-01-27; Recorded arXiv version: v1; Recorded version updated: 2026-01-27T07:46:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.20335", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.20335"}} @misc{arxiv_2601_20335, title = {{MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment}}, author = {{Qinzhuo Wu} and {Zhizhuo Yang} and {Hanhao Li} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan}}, year = {2026}, eprint = {2601.20335v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.20335v2}, note = {First published: 2026-01-28; Recorded arXiv version: v2; Recorded version updated: 2026-01-29T02:32:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.20380", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.20380"}} @misc{arxiv_2601_20380, title = {{OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution}}, author = {{Le Zhang} and {Yixiong Xiao} and {Xinjiang Lu} and {Jingjia Cao} and {Yusai Zhao} and {Jingbo Zhou} and {Lang An} and {Zikan Feng} and {Wanxiang Sha} and {Yu Shi} and {Congxi Xiao} and {Jian Xiong} and {Yankai Zhang} and {Hua Wu} and {Haifeng Wang}}, year = {2026}, eprint = {2601.20380v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.20380v1}, note = {First published: 2026-01-28; Recorded arXiv version: v1; Recorded version updated: 2026-01-28T08:45:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.20650", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.20650"}} @misc{arxiv_2601_20650, title = {{OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks}}, author = {{Jing Wu} and {Wenjie Ai} and {Daphne Barretto} and {Yiye Chen} and {Qingyu Chen} and {Yuhang He} and {Pranit Chawla} and {Nicholas Gydé} and {Yanan Jian} and {Vibhav Vineet}}, year = {2026}, eprint = {2601.20650v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.20650v3}, note = {First published: 2026-01-28; Recorded arXiv version: v3; Recorded version updated: 2026-08-26T22:31:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.20732", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.20732"}} @misc{arxiv_2601_20732, title = {{Continual GUI Agents}}, author = {{Ziwei Liu} and {Borui Kang} and {Hangjie Yuan} and {Zixiang Zhao} and {Wei Li} and {Yifan Zhu} and {Tao Feng}}, year = {2026}, eprint = {2601.20732v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.20732v4}, note = {First published: 2026-01-28; Recorded arXiv version: v4; Recorded version updated: 2026-03-25T10:25:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.21123", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.21123"}} @misc{arxiv_2601_21123, title = {{CUA-Skill: Develop Skills for Computer Using Agent}}, author = {{Tianyi Chen} and {Yinheng Li} and {Michael Solodko} and {Sen Wang} and {Nan Jiang} and {Tingyuan Cui} and {Junheng Hao} and {Jongwoo Ko} and {Sara Abdali} and {Leon Xu} and {Suzhen Zheng} and {Hao Fan} and {Pashmina Cameron} and {Justin Wagle} and {Kazuhito Koishida}}, year = {2026}, eprint = {2601.21123v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.21123v2}, note = {First published: 2026-01-28; Recorded arXiv version: v2; Recorded version updated: 2026-02-02T23:11:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.21253", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.21253"}} @misc{arxiv_2601_21253, title = {{CovAgent: Overcoming the 30\% Curse of Mobile Application Coverage with Agentic AI and Dynamic Instrumentation}}, author = {{Wei Minn} and {Biniam Fisseha Demissie} and {Yan Naing Tun} and {Jiakun Liu} and {Mariano Ceccato} and {Lwin Khin Shar} and {David Lo}}, year = {2026}, eprint = {2601.21253v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.21253v1}, note = {First published: 2026-01-29; Recorded arXiv version: v1; Recorded version updated: 2026-01-29T04:21:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.21352", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.21352"}} @misc{arxiv_2601_21352, title = {{BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI Agents}}, author = {{Ziyu Lu} and {Tengjin Weng} and {Yiying Yang} and {Yuhang Zhao} and {Xinxin Huang} and {Wenhao Jiang}}, year = {2026}, eprint = {2601.21352v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.21352v1}, note = {First published: 2026-01-29; Recorded arXiv version: v1; Recorded version updated: 2026-01-29T07:22:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.21872", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.21872"}} @misc{arxiv_2601_21872, title = {{WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents}}, author = {{Yao Zhang} and {Shijie Tang} and {Zeyu Li} and {Zhen Han} and {Volker Tresp}}, year = {2026}, eprint = {2601.21872v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.21872v2}, note = {First published: 2026-01-29; Recorded arXiv version: v2; Recorded version updated: 2026-04-09T17:48:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.21961", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.21961"}} @misc{arxiv_2601_21961, title = {{How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors}}, author = {{Kuai Yu} and {Naicheng Yu} and {Han Wang} and {Rui Yang} and {Huan Zhang}}, year = {2026}, eprint = {2601.21961v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.21961v2}, note = {First published: 2026-01-29; Recorded arXiv version: v2; Recorded version updated: 2026-02-27T16:47:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.22149", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.22149"}} @misc{arxiv_2601_22149, title = {{DynaWeb: Model-Based Reinforcement Learning of Web Agents}}, author = {{Hang Ding} and {Peidong Liu} and {Junqiao Wang} and {Ziwei Ji} and {Meng Cao} and {Rongzhao Zhang} and {Lynn Ai} and {Eric Yang} and {Tianyu Shi} and {Lei Yu}}, year = {2026}, eprint = {2601.22149v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.22149v2}, note = {First published: 2026-01-29; Recorded arXiv version: v2; Recorded version updated: 2026-04-17T18:27:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.22528", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.22528"}} @misc{arxiv_2601_22528, title = {{Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution}}, author = {{Hongze Mi} and {Yibo Feng} and {WenJie Lu} and {Song Cao} and {Jinyuan Li} and {Yanming Li} and {Xuelin Zhang} and {Haotian Luo} and {Songyang Peng} and {He Cui} and {Tengfei Tian} and {Jun Fang} and {Hua Chai} and {Naiqiang Tan}}, year = {2026}, eprint = {2601.22528v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.22528v1}, note = {First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T04:01:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2601.22781", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.22781"}} @misc{arxiv_2601_22781, title = {{Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training}}, author = {{Linjia Kang} and {Zhimin Wang} and {Yongkang Zhang} and {Duo Wu} and {Jinghe Wang} and {Ming Ma} and {Haopeng Yan} and {Zhi Wang}}, year = {2026}, eprint = {2601.22781v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.22781v1}, note = {First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T10:03:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.00575", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.00575"}} @misc{arxiv_2602_00575, title = {{Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction}}, author = {{Chaoqun Cui} and {Jing Huang} and {Shijing Wang} and {Liming Zheng} and {Qingchao Kong} and {Zhixiong Zeng}}, year = {2026}, eprint = {2602.00575v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.00575v2}, note = {First published: 2026-01-31; Recorded arXiv version: v2; Recorded version updated: 2026-07-25T06:54:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.01576", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.01576"}} @misc{arxiv_2602_01576, title = {{Generative Visual Code Mobile World Models}}, author = {{Woosung Koh} and {Sungjun Han} and {Segyu Lee} and {Se-Young Yun} and {Jamin Shin}}, year = {2026}, eprint = {2602.01576v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.01576v2}, note = {First published: 2026-02-02; Recorded arXiv version: v2; Recorded version updated: 2026-05-23T02:41:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.01725", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.01725"}} @misc{arxiv_2602_01725, title = {{SafePred: A Predictive Guardrail for Computer-Using Agents via World Models}}, author = {{Yurun Chen} and {Zeyi Liao} and {Ping Yin} and {Taotao Xie} and {Keting Yin} and {Shengyu Zhang}}, year = {2026}, eprint = {2602.01725v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.01725v1}, note = {First published: 2026-02-02; Recorded arXiv version: v1; Recorded version updated: 2026-02-02T07:04:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.02419", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.02419"}} @misc{arxiv_2602_02419, title = {{SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration}}, author = {{Qingni Wang} and {Yue Fan} and {Xin Eric Wang}}, year = {2026}, eprint = {2602.02419v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02419v2}, note = {First published: 2026-02-02; Recorded arXiv version: v2; Recorded version updated: 2026-02-03T08:31:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.02468", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.02468"}} @misc{arxiv_2602_02468, title = {{Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts}}, author = {{Aiden Yiliu Li} and {Xinyue Hao} and {Shilong Liu} and {Mengdi Wang}}, year = {2026}, eprint = {2602.02468v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02468v1}, note = {First published: 2026-02-02; Recorded arXiv version: v1; Recorded version updated: 2026-02-02T18:50:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.02548", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.02548"}} @misc{arxiv_2602_02548, title = {{ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents}}, author = {{Xiaoce Wang} and {Guibin Zhang} and {Junzhe Li} and {Jinzhe Tu} and {Chun Li} and {Ming Li}}, year = {2026}, eprint = {2602.02548v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02548v1}, note = {First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T08:38:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.02995", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.02995"}} @misc{arxiv_2602_02995, title = {{Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents}}, author = {{Sizhe Tang} and {Rongqian Chen} and {Tian Lan}}, year = {2026}, eprint = {2602.02995v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02995v1}, note = {First published: 2026-02-03; Recorded arXiv version: v1; Recorded version updated: 2026-02-03T02:07:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.03792", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.03792"}} @misc{arxiv_2602_03792, title = {{WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents}}, author = {{Xilong Wang} and {Yinuo Liu} and {Zhun Wang} and {Dawn Song} and {Neil Gong}}, year = {2026}, eprint = {2602.03792v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.03792v1}, note = {First published: 2026-02-03; Recorded arXiv version: v1; Recorded version updated: 2026-02-03T17:55:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.05354", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.05354"}} @misc{arxiv_2602_05354, title = {{Do Web Agents Investigate Before They Decide?}}, author = {{Syed Nazmus Sakib} and {Nafiul Haque} and {Tapodhir Karmakar Taton} and {Shahrear Bin Amin} and {Shifat E. Arman}}, year = {2026}, eprint = {2602.05354v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.05354v3}, note = {First published: 2026-02-05; Recorded arXiv version: v3; Recorded version updated: 2026-09-08T14:40:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.05429", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.05429"}} @misc{arxiv_2602_05429, title = {{M\$\textasciicircum{}2\$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining}}, author = {{Rui Lv} and {Juncheng Mo} and {Tianyi Chu} and {Chen Rao} and {Hongyi Jing} and {Jiajie Teng} and {Jiafu Chen} and {Shiqi Zhang} and {Liangzi Ding} and {Shuo Fang} and {Huaizhong Lin} and {Ziqiang Dang} and {Chenguang Ma} and {Lei Zhao}}, year = {2026}, eprint = {2602.05429v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.05429v1}, note = {First published: 2026-02-05; Recorded arXiv version: v1; Recorded version updated: 2026-02-05T08:19:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.05832", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.05832"}} @misc{arxiv_2602_05832, title = {{UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents}}, author = {{Han Xiao} and {Guozhi Wang} and {Hao Wang} and {Shilong Liu} and {Yuxiang Chai} and {Yue Pan} and {Yufeng Zhou} and {Xiaoxin Chen} and {Yafei Wen} and {Hongsheng Li}}, year = {2026}, eprint = {2602.05832v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.05832v1}, note = {First published: 2026-02-05; Recorded arXiv version: v1; Recorded version updated: 2026-02-05T16:21:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.06075", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.06075"}} @misc{arxiv_2602_06075, title = {{MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments}}, author = {{Guangyi Liu} and {Pengxiang Zhao} and {Yaozhen Liang} and {Qinyi Luo} and {Shunye Tang} and {Yuxiang Chai} and {Weifeng Lin} and {Han Xiao} and {WenHao Wang} and {Siheng Chen} and {Zhengxi Lu} and {Gao Wu} and {Hao Wang} and {Liang Liu} and {Yong Liu}}, year = {2026}, eprint = {2602.06075v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.06075v3}, note = {First published: 2026-02-03; Recorded arXiv version: v3; Recorded version updated: 2026-08-27T06:48:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.06351", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.06351"}} @misc{arxiv_2602_06351, title = {{Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion}}, author = {{Longhui Ma} and {Di Zhao} and {Siwei Wang} and {Zhao Lv} and {Miao Wang}}, year = {2026}, eprint = {2602.06351v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.06351v1}, note = {First published: 2026-02-06; Recorded arXiv version: v1; Recorded version updated: 2026-02-06T03:27:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.06391", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.06391"}} @misc{arxiv_2602_06391, title = {{POINTS-GUI-G: GUI-Grounding Journey}}, author = {{Zhongyin Zhao} and {Yuan Liu} and {Yikun Liu} and {Haicheng Wang} and {Le Tian} and {Xiao Zhou} and {Yangxiu You} and {Zilin Yu} and {Yang Yu} and {Jie Zhou}}, year = {2026}, eprint = {2602.06391v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.06391v1}, note = {First published: 2026-02-06; Recorded arXiv version: v1; Recorded version updated: 2026-02-06T05:14:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.07153", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.07153"}} @misc{arxiv_2602_07153, title = {{ANCHOR: Branch-Point Data Generation for GUI Agents}}, author = {{Jinbiao Wei} and {Yilun Zhao} and {Kangqi Ni} and {Arman Cohan}}, year = {2026}, eprint = {2602.07153v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.07153v2}, note = {First published: 2026-02-06; Recorded arXiv version: v2; Recorded version updated: 2026-04-12T06:09:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.07283", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.07283"}} @misc{arxiv_2602_07283, title = {{Mapping the Design Space of User Experience for Computer Use Agents}}, author = {{Ruijia Cheng} and {Jenny T. Liang} and {Eldon Schoop} and {Jeffrey Nichols}}, year = {2026}, eprint = {2602.07283v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.07283v1}, note = {First published: 2026-02-07; Recorded arXiv version: v1; Recorded version updated: 2026-02-07T00:19:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.08995", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.08995"}} @misc{arxiv_2602_08995, title = {{When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents}}, author = {{Yuting Ning} and {Jaylen Jones} and {Zhehao Zhang} and {Chentao Ye} and {Weitong Ruan} and {Junyi Li} and {Rahul Gupta} and {Huan Sun}}, year = {2026}, eprint = {2602.08995v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.08995v2}, note = {First published: 2026-02-09; Recorded arXiv version: v2; Recorded version updated: 2026-06-25T04:36:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.09007", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.09007"}} @misc{arxiv_2602_09007, title = {{GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments}}, author = {{Haodong Li} and {Jingwei Wu} and {Quan Sun} and {Guopeng Li} and {Juanxi Tian} and {Ziyu Guo} and {Donghao Zhou} and {Tianfei Ren} and {Huanyu Zhang} and {Yanlin Lai} and {Ruichuan An} and {Hongbo Peng} and {Yuhong Dai} and {Jia Wang} and {Ziyang Meng} and {Zheng Ge} and {Xiangyu Zhang} and {Daxin Jiang} and {Pheng-Ann Heng}}, year = {2026}, eprint = {2602.09007v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.09007v3}, note = {First published: 2026-02-09; Recorded arXiv version: v3; Recorded version updated: 2026-09-26T18:28:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.09012", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.09012"}} @misc{arxiv_2602_09012, title = {{Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense}}, author = {{Jiacheng Liu} and {Yaxin Luo} and {Jiacheng Cui} and {Xinyi Shang} and {Xiaohan Zhao} and {Zhiqiang Shen}}, year = {2026}, eprint = {2602.09012v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.09012v2}, note = {First published: 2026-02-09; Recorded arXiv version: v2; Recorded version updated: 2026-06-21T08:25:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.09082", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.09082"}} @misc{arxiv_2602_09082, title = {{UI-Venus-1.5 Technical Report}}, author = {{Venus Team} and {Changlong Gao} and {Zhangxuan Gu} and {Yulin Liu} and {Xinyu Qiu} and {Shuheng Shen} and {Yue Wen} and {Tianyu Xia} and {Zhenyu Xu} and {Zhengwen Zeng} and {Beitong Zhou} and {Xingran Zhou} and {Weizhi Chen} and {Sunhao Dai} and {Jingya Dou} and {Yichen Gong} and {Yuan Guo} and {Zhenlin Guo} and {Feng Li} and {Qian Li} and {Jinzhen Lin} and {Yuqi Zhou} and {Linchao Zhu} and {Liang Chen} and {Zhenyu Guo} and {Changhua Meng} and {Weiqiang Wang}}, year = {2026}, eprint = {2602.09082v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.09082v2}, note = {First published: 2026-02-09; Recorded arXiv version: v2; Recorded version updated: 2026-02-24T15:17:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.09310", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.09310"}} @misc{arxiv_2602_09310, title = {{A11y-CUA Dataset: Characterizing the Accessibility Gap in Computer Use Agents}}, author = {{Ananya Gubbi Mohanbabu} and {Rosiana Natalie} and {Brandon Kim} and {Anhong Guo} and {Amy Pavel}}, year = {2026}, eprint = {2602.09310v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.09310v1}, note = {First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T01:00:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.09662", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.09662"}} @misc{arxiv_2602_09662, title = {{TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution}}, author = {{Deyang Jiang} and {Jing Huang} and {Xuanle Zhao} and {Lei Chen} and {Liming Zheng} and {Fanfan Liu} and {Haibo Qiu} and {Peng Shi} and {Zhixiong Zeng}}, year = {2026}, eprint = {2602.09662v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.09662v1}, note = {First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T11:16:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.09856", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.09856"}} @misc{arxiv_2602_09856, title = {{Code2World: A GUI World Model via Renderable Code Generation}}, author = {{Yuhao Zheng} and {Li'an Zhong} and {Yi Wang} and {Rui Dai} and {Kaikui Liu} and {Xiangxiang Chu} and {Linyuan Lv} and {Philip Torr} and {Kevin Qinghong Lin}}, year = {2026}, eprint = {2602.09856v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.09856v1}, note = {First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T14:56:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.10139", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.10139"}} @misc{arxiv_2602_10139, title = {{Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible}}, author = {{Lepeng Zhao} and {Zhenhua Zou} and {Shuo Li} and {Zhuotao Liu}}, year = {2026}, eprint = {2602.10139v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.10139v3}, note = {First published: 2026-02-08; Recorded arXiv version: v3; Recorded version updated: 2026-04-26T01:34:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.10356", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.10356"}} @misc{arxiv_2602_10356, title = {{Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents}}, author = {{Tianci Xue} and {Zeyi Liao} and {Tianneng Shi} and {Zilu Wang} and {Kai Zhang} and {Dawn Song} and {Yu Su} and {Huan Sun}}, year = {2026}, eprint = {2602.10356v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.10356v2}, note = {First published: 2026-02-10; Recorded arXiv version: v2; Recorded version updated: 2026-05-11T00:11:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.10814", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.10814"}} @misc{arxiv_2602_10814, title = {{See, Plan, Snap: Evaluating Multimodal GUI Agents in Scratch}}, author = {{Xingyi Zhang} and {Yulei Ye} and {Kaifeng Huang} and {Wenhao Li} and {Xiangfeng Wang}}, year = {2026}, eprint = {2602.10814v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.10814v1}, note = {First published: 2026-02-11; Recorded arXiv version: v1; Recorded version updated: 2026-02-11T12:54:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.11524", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.11524"}} @misc{arxiv_2602_11524, title = {{Adaptive Milestone Reward for GUI Agents}}, author = {{Congmin Zheng} and {Xiaoyun Mo} and {Xinbei Ma} and {Qiqiang Lin} and {Yin Zhao} and {Jiachen Zhu} and {Xingyu Lou} and {Jun Wang} and {Zhaoxiang Wang} and {Weiwen Liu} and {Zhuosheng Zhang} and {Yong Yu} and {Weinan Zhang}}, year = {2026}, eprint = {2602.11524v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.11524v1}, note = {First published: 2026-02-12; Recorded arXiv version: v1; Recorded version updated: 2026-02-12T03:31:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.11724", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.11724"}} @misc{arxiv_2602_11724, title = {{WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements}}, author = {{Xiwen Teoh} and {Yun Lin} and {Duc-Minh Nguyen} and {Ruofei Ren} and {Wenjie Zhang} and {Jin Song Dong}}, year = {2026}, eprint = {2602.11724v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.11724v3}, note = {First published: 2026-02-12; Recorded arXiv version: v3; Recorded version updated: 2026-04-23T15:00:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.11750", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.11750"}} @misc{arxiv_2602_11750, title = {{AmbiBench: Benchmarking Mobile GUI Agents Beyond One-Shot Instructions in the Wild}}, author = {{Jiazheng Sun} and {Mingxuan Li} and {Yingying Zhang} and {Jiayang Niu} and {Yachen Wu} and {Ruihan Jin} and {Shuyu Lei} and {Pengrongrui Tan} and {Zongyu Zhang} and {Ruoyi Wang} and {Jiachen Yang} and {Boyu Yang} and {Jiacheng Liu} and {Xin Peng}}, year = {2026}, eprint = {2602.11750v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.11750v1}, note = {First published: 2026-02-12; Recorded arXiv version: v1; Recorded version updated: 2026-02-12T09:25:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.12276", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.12276"}} @misc{arxiv_2602_12276, title = {{Agentic Test-Time Scaling for WebAgents}}, author = {{Nicholas Lee} and {Lutfi Eren Erdogan} and {Chris Joseph John} and {Surya Krishnapillai} and {Michael W. Mahoney} and {Kurt Keutzer} and {Amir Gholami}}, year = {2026}, eprint = {2602.12276v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.12276v2}, note = {First published: 2026-02-12; Recorded arXiv version: v2; Recorded version updated: 2026-08-14T21:25:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.12430", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2602.12430"}} @misc{arxiv_2602_12430, title = {{Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward}}, author = {{Renjun Xu} and {Yang Yan}}, year = {2026}, eprint = {2602.12430v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.12430v4}, note = {First published: 2026-02-12; Recorded arXiv version: v4; Recorded version updated: 2026-06-02T16:14:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.12544", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.12544"}} @misc{arxiv_2602_12544, title = {{Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation}}, author = {{Lajanugen Logeswaran} and {Jaekyeom Kim} and {Sungryull Sohn} and {Creighton Glasscock} and {Honglak Lee}}, year = {2026}, eprint = {2602.12544v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.12544v1}, note = {First published: 2026-02-13; Recorded arXiv version: v1; Recorded version updated: 2026-02-13T02:52:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.13516", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.13516"}} @misc{arxiv_2602_13516, title = {{SPILLage: Agentic Oversharing on the Web}}, author = {{Jaechul Roh} and {Eugene Bagdasarian} and {Hamed Haddadi} and {Ali Shahin Shamsabadi}}, year = {2026}, eprint = {2602.13516v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.13516v1}, note = {First published: 2026-02-13; Recorded arXiv version: v1; Recorded version updated: 2026-02-13T23:02:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.13559", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.13559"}} @misc{arxiv_2602_13559, title = {{OpAgent: Operator Agent for Web Navigation}}, author = {{Yuyu Guo} and {Wenjie Yang} and {Siyuan Yang} and {Ziyang Liu} and {Cheng Chen} and {Yuan Wei} and {Yun Hu} and {Yang Huang} and {Guoliang Hao} and {Dongsheng Yuan} and {Jianming Wang} and {Xin Chen} and {Hang Yu} and {Lei Lei} and {Peng Di}}, year = {2026}, eprint = {2602.13559v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.13559v2}, note = {First published: 2026-02-14; Recorded arXiv version: v2; Recorded version updated: 2026-04-30T02:05:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.13653", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.13653"}} @misc{arxiv_2602_13653, title = {{Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization}}, author = {{Yibo Wang} and {Guangda Huzhang} and {Yuwei Hu} and {Yu Xia} and {Shiyin Lu} and {Qing-Guo Chen} and {Zhao Xu} and {Weihua Luo} and {Kaifu Zhang} and {Lijun Zhang}}, year = {2026}, eprint = {2602.13653v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.13653v1}, note = {First published: 2026-02-14; Recorded arXiv version: v1; Recorded version updated: 2026-02-14T07:44:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.14093", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.14093"}} @misc{arxiv_2602_14093, title = {{GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training}}, author = {{Yuan Cao} and {Dezhi Ran} and {Mengzhou Wu} and {Yuzhe Guo} and {Xin Chen} and {Ang Li} and {Gang Cao} and {Gong Zhi} and {Hao Yu} and {Linyi Li} and {Wei Yang} and {Tao Xie}}, year = {2026}, eprint = {2602.14093v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.14093v1}, note = {First published: 2026-02-15; Recorded arXiv version: v1; Recorded version updated: 2026-02-15T10:58:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.14276", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.14276"}} @misc{arxiv_2602_14276, title = {{ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision}}, author = {{A. Said Gurbuz} and {Sunghwan Hong} and {Ahmed Nassar} and {Marc Pollefeys} and {Peter Staar}}, year = {2026}, eprint = {2602.14276v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.14276v2}, note = {First published: 2026-02-15; Recorded arXiv version: v2; Recorded version updated: 2026-05-01T17:32:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.14296", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.14296"}} @misc{arxiv_2602_14296, title = {{AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines}}, author = {{Yifan Wu} and {Yiran Peng} and {Yiyu Chen} and {Jianhao Ruan} and {Zijie Zhuang} and {Cheng Yang} and {Jiayi Zhang} and {Man Chen} and {Yenchi Tseng} and {Zhaoyang Yu} and {Liang Chen} and {Yuyao Zhai} and {Bang Liu} and {Chenglin Wu} and {Yuyu Luo}}, year = {2026}, eprint = {2602.14296v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.14296v1}, note = {First published: 2026-02-15; Recorded arXiv version: v1; Recorded version updated: 2026-02-15T20:03:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.14721", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.14721"}} @misc{arxiv_2602_14721, title = {{WebWorld: A Large-Scale World Model for Web Agent Training}}, author = {{Zikai Xiao} and {Jianhong Tu} and {Chuhang Zou} and {Yuxin Zuo} and {Zhi Li} and {Peng Wang} and {Bowen Yu} and {Fei Huang} and {Junyang Lin} and {Zuozhu Liu}}, year = {2026}, eprint = {2602.14721v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.14721v1}, note = {First published: 2026-02-16; Recorded arXiv version: v1; Recorded version updated: 2026-02-16T13:06:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.14865", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.14865"}} @misc{arxiv_2602_14865, title = {{EmbeWebAgent: Embedding Web Agents into Any Customized UI}}, author = {{Chenyang Ma} and {Clyde Fare} and {Matthew Wilson} and {Dave Braines}}, year = {2026}, eprint = {2602.14865v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.14865v1}, note = {First published: 2026-02-16; Recorded arXiv version: v1; Recorded version updated: 2026-02-16T15:59:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.16313", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.16313"}} @misc{arxiv_2602_16313, title = {{MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks}}, author = {{Zexue He} and {Yu Wang} and {Churan Zhi} and {Yuanzhe Hu} and {Tzu-Ping Chen} and {Lang Yin} and {Ze Chen} and {Tong Arthur Wu} and {Siru Ouyang} and {Zihan Wang} and {Jiaxin Pei} and {Julian McAuley} and {Yejin Choi} and {Alex Pentland}}, year = {2026}, eprint = {2602.16313v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.16313v2}, note = {First published: 2026-02-18; Recorded arXiv version: v2; Recorded version updated: 2026-09-17T22:55:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.16855", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.16855"}} @misc{arxiv_2602_16855, title = {{Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents}}, author = {{Haiyang Xu} and {Xi Zhang} and {Haowei Liu} and {Junyang Wang} and {Zhaozai Zhu} and {Shengjie Zhou} and {Xuhao Hu} and {Feiyu Gao} and {Junjie Cao} and {Zihua Wang} and {Zhiyuan Chen} and {Jitong Liao} and {Qi Zheng} and {Jiahui Zeng} and {Ze Xu} and {Shuai Bai} and {Junyang Lin} and {Jingren Zhou} and {Ming Yan}}, year = {2026}, eprint = {2602.16855v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.16855v1}, note = {First published: 2026-02-15; Recorded arXiv version: v1; Recorded version updated: 2026-02-15T01:52:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.17003", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.17003"}} @misc{arxiv_2602_17003, title = {{Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History}}, author = {{Serin Kim} and {Sangam Lee} and {Dongha Lee}}, year = {2026}, eprint = {2602.17003v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.17003v3}, note = {First published: 2026-02-19; Recorded arXiv version: v3; Recorded version updated: 2026-05-27T12:15:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.17365", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.17365"}} @misc{arxiv_2602_17365, title = {{Computer-Using World Model}}, author = {{Yiming Guan} and {Rui Yu} and {John Zhang} and {Lu Wang} and {Chaoyun Zhang} and {Liqun Li} and {Bo Qiao} and {Si Qin} and {He Huang} and {Fangkai Yang} and {Pu Zhao} and {Lukas Wutschitz} and {Samuel Kessler} and {Huseyin A Inan} and {Robert Sim} and {Saravan Rajmohan} and {Qingwei Lin} and {Dongmei Zhang}}, year = {2026}, eprint = {2602.17365v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.17365v1}, note = {First published: 2026-02-19; Recorded arXiv version: v1; Recorded version updated: 2026-02-19T13:48:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.17588", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.17588"}} @misc{arxiv_2602_17588, title = {{Modeling Distinct Human Interaction in Web Agents}}, author = {{Faria Huq} and {Zora Zhiruo Wang} and {Zhanqiu Guo} and {Venu Arvind Arangarajan} and {Tianyue Ou} and {Frank Xu} and {Shuyan Zhou} and {Graham Neubig} and {Jeffrey P. Bigham}}, year = {2026}, eprint = {2602.17588v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.17588v4}, note = {First published: 2026-02-19; Recorded arXiv version: v4; Recorded version updated: 2026-07-07T23:37:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2602.20502", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.20502"}} @misc{arxiv_2602_20502, title = {{ActionEngine: From Reactive to Programmatic Web Agents via State Machine Memory}}, author = {{Hongbin Zhong} and {Fazle Faisal} and {Luis França} and {Tanakorn Leesatapornwongsa} and {Adriana Szekeres} and {Kexin Rong} and {Suman Nath}}, year = {2026}, eprint = {2602.20502v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.20502v2}, note = {First published: 2026-02-24; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T17:40:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.00476", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.00476"}} @misc{arxiv_2603_00476, title = {{Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents}}, author = {{Linxi Jiang} and {Zhijie Liu} and {Haotian Luo} and {Zhiqiang Lin}}, year = {2026}, eprint = {2603.00476v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.00476v1}, note = {First published: 2026-02-28; Recorded arXiv version: v1; Recorded version updated: 2026-02-28T05:25:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.02951", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.02951"}} @misc{arxiv_2603_02951, title = {{CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning}}, author = {{Zhenquan Yao} and {Zitong Huang} and {Yihan Zeng} and {Jianhua Han} and {Hang Xu} and {Chun-Mei Feng} and {Jianwei Ma} and {Wangmeng Zuo}}, year = {2026}, eprint = {2603.02951v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.02951v2}, note = {First published: 2026-03-03; Recorded arXiv version: v2; Recorded version updated: 2026-03-07T10:11:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.04364", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.04364"}} @misc{arxiv_2603_04364, title = {{Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks}}, author = {{Haoyu Liu} and {Dingcheng Li} and {Lukas Rutishauser} and {Zeyu Zheng}}, year = {2026}, eprint = {2603.04364v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.04364v2}, note = {First published: 2026-03-04; Recorded arXiv version: v2; Recorded version updated: 2026-10-05T23:01:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.04949", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.04949"}} @misc{arxiv_2603_04949, title = {{TimeWarp: Evaluating Web Agents by Revisiting the Past}}, author = {{Md Farhan Ishmam} and {Kenneth Marino}}, year = {2026}, eprint = {2603.04949v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.04949v4}, note = {First published: 2026-03-05; Recorded arXiv version: v4; Recorded version updated: 2026-10-14T10:16:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.05044", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.05044"}} @misc{arxiv_2603_05044, title = {{WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents}}, author = {{Sicheng Fan} and {Qingyun Shi} and {Shengze Xu} and {Shengbo Cai} and {Tieyong Zeng} and {Li Ling} and {Yanyi Shang} and {Dehan Kong}}, year = {2026}, eprint = {2603.05044v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.05044v2}, note = {First published: 2026-03-05; Recorded arXiv version: v2; Recorded version updated: 2026-04-14T08:14:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.05295", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.05295"}} @misc{arxiv_2603_05295, title = {{WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces}}, author = {{Sicheng Fan} and {Rui Wan} and {Yifei Leng} and {Gaoning Liang} and {Li Ling} and {Yanyi Shang} and {Dehan Kong}}, year = {2026}, eprint = {2603.05295v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.05295v3}, note = {First published: 2026-03-05; Recorded arXiv version: v3; Recorded version updated: 2026-04-14T08:41:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.07432", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.07432"}} @misc{arxiv_2603_07432, title = {{Generalization in Online Reinforcement Learning for Mobile Agents}}, author = {{Li Gu} and {Zihuan Jiang} and {Zhixiang Chi} and {Huan Liu} and {Ziqiang Wang} and {Yuanhao Yu} and {Glen Berseth} and {Yang Wang}}, year = {2026}, eprint = {2603.07432v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.07432v1}, note = {First published: 2026-03-08; Recorded arXiv version: v1; Recorded version updated: 2026-03-08T03:08:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.07978", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.07978"}} @misc{arxiv_2603_07978, title = {{OSExpert: Computer-Use Agents Learning Professional Skills via Exploration}}, author = {{Jiateng Liu} and {Zhenhailong Wang} and {Rushi Wang} and {Bingxuan Li} and {Jeonghwan Kim} and {Aditi Tiwari} and {Pengfei Yu} and {Denghui Zhang} and {Heng Ji}}, year = {2026}, eprint = {2603.07978v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.07978v1}, note = {First published: 2026-03-09; Recorded arXiv version: v1; Recorded version updated: 2026-03-09T05:27:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.08013", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.08013"}} @misc{arxiv_2603_08013, title = {{PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents}}, author = {{Yuxiang Chai} and {Shunye Tang} and {Han Xiao} and {Rui Liu} and {Hongsheng Li}}, year = {2026}, eprint = {2603.08013v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.08013v1}, note = {First published: 2026-03-09; Recorded arXiv version: v1; Recorded version updated: 2026-03-09T06:41:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.08533", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.08533"}} @misc{arxiv_2603_08533, title = {{SecAgent: Efficient Mobile GUI Agent with Semantic Context}}, author = {{Yiping Xie} and {Song Chen} and {Jingxuan Xing} and {Wei Jiang} and {Zekun Zhu} and {Yingyao Wang} and {Pi Bu} and {Jun Song} and {Yuning Jiang} and {Bo Zheng}}, year = {2026}, eprint = {2603.08533v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.08533v2}, note = {First published: 2026-03-09; Recorded arXiv version: v2; Recorded version updated: 2026-03-31T03:08:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.10178", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.10178"}} @misc{arxiv_2603_10178, title = {{Video-Based Reward Modeling for Computer-Use Agents}}, author = {{Linxin Song} and {Jieyu Zhang} and {Huanxin Sheng} and {Taiwei Shi} and {Gupta Rahul} and {Yang Liu} and {Ranjay Krishna} and {Jian Kang} and {Jieyu Zhao}}, year = {2026}, eprint = {2603.10178v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.10178v1}, note = {First published: 2026-03-10; Recorded arXiv version: v1; Recorded version updated: 2026-03-10T19:17:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.10268", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.10268"}} @misc{arxiv_2603_10268, title = {{SpecOps: A Fully Automated AI Agent Testing Framework in Real-World GUI Environments}}, author = {{Syed Yusuf Ahmed} and {Shiwei Feng} and {Chanwoo Bae} and {Calix Barrus Xiangyu Zhang}}, year = {2026}, eprint = {2603.10268v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.10268v1}, note = {First published: 2026-03-10; Recorded arXiv version: v1; Recorded version updated: 2026-03-10T22:56:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.10505", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.10505"}} @misc{arxiv_2603_10505, title = {{Safe and Scalable Web Agent Learning via Recreated Websites}}, author = {{Hyungjoo Chae} and {Jungsoo Park} and {Alan Ritter}}, year = {2026}, eprint = {2603.10505v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.10505v1}, note = {First published: 2026-03-11; Recorded arXiv version: v1; Recorded version updated: 2026-03-11T07:58:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.10577", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.10577"}} @misc{arxiv_2603_10577, title = {{CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents}}, author = {{Marta Sumyk} and {Oleksandr Kosovan}}, year = {2026}, eprint = {2603.10577v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.10577v2}, note = {First published: 2026-03-11; Recorded arXiv version: v2; Recorded version updated: 2026-03-12T07:30:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.10664", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2603.10664"}} @misc{arxiv_2603_10664, title = {{Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration}}, author = {{Alexandre De Masi}}, year = {2026}, eprint = {2603.10664v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.10664v1}, note = {First published: 2026-03-11; Recorded arXiv version: v1; Recorded version updated: 2026-03-11T11:24:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.12138", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.12138"}} @misc{arxiv_2603_12138, title = {{HATS: Hardness-Aware Trajectory Synthesis for GUI Agents}}, author = {{Rui Shao} and {Ruize Gao} and {Bin Xie} and {Yixing Li} and {Kaiwen Zhou} and {Shuai Wang} and {Weili Guan} and {Gongwei Chen}}, year = {2026}, eprint = {2603.12138v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.12138v1}, note = {First published: 2026-03-12; Recorded arXiv version: v1; Recorded version updated: 2026-03-12T16:40:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.12823", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.12823"}} @misc{arxiv_2603_12823, title = {{Adaptive Vision-Language Model Routing for Computer Use Agents}}, author = {{Xunzhuo Liu} and {Bowei He} and {Xue Liu} and {Andy Luo} and {Haichen Zhang} and {Huamin Chen}}, year = {2026}, eprint = {2603.12823v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.12823v1}, note = {First published: 2026-03-13; Recorded arXiv version: v1; Recorded version updated: 2026-03-13T09:21:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.14448", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.14448"}} @misc{arxiv_2603_14448, title = {{Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements}}, author = {{Ziwei Liu} and {Tao Feng} and {Borui Kang} and {Yanbing Yang} and {Jun Luo}}, year = {2026}, eprint = {2603.14448v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.14448v1}, note = {First published: 2026-03-15; Recorded arXiv version: v1; Recorded version updated: 2026-03-15T15:47:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.14707", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.14707"}} @misc{arxiv_2603_14707, title = {{Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents}}, author = {{Xunzhuo Liu} and {Bowei He} and {Xue Liu} and {Andy Luo} and {Haichen Zhang} and {Huamin Chen}}, year = {2026}, eprint = {2603.14707v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.14707v1}, note = {First published: 2026-03-16; Recorded arXiv version: v1; Recorded version updated: 2026-03-16T01:31:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.15039", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.15039"}} @misc{arxiv_2603_15039, title = {{GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents}}, author = {{Yang Li} and {Yuchen Liu} and {Haoyu Lu} and {Zhiqiang Xia} and {Hongzhen Wang} and {Kaiyang Han} and {Changpeng Yang} and {Jinyang Wu} and {Jiaming Xu} and {Runyu Shi} and {Ying Huang}}, year = {2026}, eprint = {2603.15039v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.15039v1}, note = {First published: 2026-03-16; Recorded arXiv version: v1; Recorded version updated: 2026-03-16T09:45:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.15714", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.15714"}} @misc{arxiv_2603_15714, title = {{How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition}}, author = {{Mateusz Dziemian} and {Maxwell Lin} and {Xiaohan Fu} and {Micha Nowak} and {Nick Winter} and {Eliot Jones} and {Andy Zou} and {Lama Ahmad} and {Kamalika Chaudhuri} and {Sahana Chennabasappa} and {Xander Davies} and {Lauren Deason} and {Benjamin L. Edelman} and {Tanner Emek} and {Ivan Evtimov} and {Jim Gust} and {Maia Hamin} and {Kat He} and {Klaudia Krawiecka} and {Riccardo Patana} and {Neil Perry} and {Troy Peterson} and {Xiangyu Qi} and {Javier Rando} and {Zifan Wang} and {Zihan Wang} and {Spencer Whitman} and {Eric Winsor} and {Arman Zharmagambetov} and {Matt Fredrikson} and {Zico Kolter}}, year = {2026}, eprint = {2603.15714v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.15714v1}, note = {First published: 2026-03-16; Recorded arXiv version: v1; Recorded version updated: 2026-03-16T14:49:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.17357", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.17357"}} @misc{arxiv_2603_17357, title = {{WebPII: Benchmarking Visual PII Detection for Computer-Use Agents}}, author = {{Nathan Zhao}}, year = {2026}, eprint = {2603.17357v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.17357v1}, note = {First published: 2026-03-18; Recorded arXiv version: v1; Recorded version updated: 2026-03-18T04:41:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.17441", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.17441"}} @misc{arxiv_2603_17441, title = {{AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement}}, author = {{Siqi Pei} and {Liang Tang} and {Tiaonan Duan} and {Long Chen} and {Shuxian Li} and {Kaer Huang} and {Yanzhe Jing} and {Yiqiang Yan} and {Bo Zhang} and {Chenghao Jiang} and {Borui Zhang} and {Jiwen Lu}}, year = {2026}, eprint = {2603.17441v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.17441v1}, note = {First published: 2026-03-18; Recorded arXiv version: v1; Recorded version updated: 2026-03-18T07:26:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.18429", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.18429"}} @misc{arxiv_2603_18429, title = {{AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents}}, author = {{Yibo Shi} and {Jungang Li} and {Linghao Zhang} and {Zihao Dongfang} and {Biao Wu} and {Sicheng Tao} and {Yibo Yan} and {Chenxi Qin} and {Weiting Liu} and {Zhixin Lin} and {Hanqian Li} and {Yu Huang} and {Song Dai} and {Yonghua Hei} and {Yue Ding} and {Xiang Li} and {Shikang Wang} and {Chengdong Xu} and {Jingqi Liu} and {Xueying Ma} and {Zhiwen Zheng} and {Xiaofei Zhang} and {Bincheng Wang} and {Nichen Yang} and {Jie Wu} and {Lihua Tian} and {Chen Li} and {Xuming Hu}}, year = {2026}, eprint = {2603.18429v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.18429v1}, note = {First published: 2026-03-19; Recorded arXiv version: v1; Recorded version updated: 2026-03-19T02:45:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.18762", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.18762"}} @misc{arxiv_2603_18762, title = {{ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation}}, author = {{Haochen Zhao} and {Shaoyang Cui}}, year = {2026}, eprint = {2603.18762v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.18762v1}, note = {First published: 2026-03-19; Recorded arXiv version: v1; Recorded version updated: 2026-03-19T11:14:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.19191", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.19191"}} @misc{arxiv_2603_19191, title = {{OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards}}, author = {{Zehao Li} and {Zhenyu Wu} and {Yibo Zhao} and {Bowen Yang} and {Jingjing Xie} and {Zhaoyang Liu} and {Zhoumianze Liu} and {Kaiming Jin} and {Jianze Liang} and {Zonglin Li} and {Feng Wu} and {Bowen Zhou} and {Zun Wang} and {Zichen Ding}}, year = {2026}, eprint = {2603.19191v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.19191v1}, note = {First published: 2026-03-19; Recorded arXiv version: v1; Recorded version updated: 2026-03-19T17:47:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.19685", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.19685"}} @misc{arxiv_2603_19685, title = {{A Subgoal-driven Framework for Improving Long-Horizon LLM Agents}}, author = {{Taiyi Wang} and {Sian Gooding} and {Florian Hartmann} and {Oriana Riva} and {Edward Grefenstette}}, year = {2026}, eprint = {2603.19685v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.19685v1}, note = {First published: 2026-03-20; Recorded arXiv version: v1; Recorded version updated: 2026-03-20T06:32:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.19993", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.19993"}} @misc{arxiv_2603_19993, title = {{MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI}}, author = {{Rozain Shakeel} and {Abdul Rahman Mohammad Ali} and {Muneeb Mushtaq} and {Tausifa Jan Saleem} and {Tajamul Ashraf}}, year = {2026}, eprint = {2603.19993v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.19993v1}, note = {First published: 2026-03-20; Recorded arXiv version: v1; Recorded version updated: 2026-03-20T14:43:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.20340", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.20340"}} @misc{arxiv_2603_20340, title = {{ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents}}, author = {{Zijian Lu} and {Yiping Zuo} and {Yupeng Nie} and {Xin He} and {Weibei Fan} and {Lianyong Qi} and {Shi Jin}}, year = {2026}, eprint = {2603.20340v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.20340v3}, note = {First published: 2026-03-20; Recorded arXiv version: v3; Recorded version updated: 2026-04-15T07:34:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.20351", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.20351"}} @misc{arxiv_2603_20351, title = {{MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation}}, author = {{Yizhe Zhao} and {Yongjian Fu} and {Zihao Feng} and {Hao Pan} and {Yongheng Deng} and {Yaoxue Zhang} and {Ju Ren}}, year = {2026}, eprint = {2603.20351v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.20351v1}, note = {First published: 2026-03-20; Recorded arXiv version: v1; Recorded version updated: 2026-03-20T12:19:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.22529", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.22529"}} @misc{arxiv_2603_22529, title = {{Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos}}, author = {{Shoubin Yu} and {Lei Shu} and {Antoine Yang} and {Yao Fu} and {Srinivas Sunkara} and {Maria Wang} and {Jindong Chen} and {Mohit Bansal} and {Boqing Gong}}, year = {2026}, eprint = {2603.22529v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.22529v1}, note = {First published: 2026-03-23; Recorded arXiv version: v1; Recorded version updated: 2026-03-23T19:47:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.23007", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.23007"}} @misc{arxiv_2603_23007, title = {{AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents}}, author = {{Yutao Luo} and {Haotian Zhu} and {Shuchao Pang} and {Zhigang Lu} and {Tian Dong} and {Yongbin Zhou} and {Minhui Xue}}, year = {2026}, eprint = {2603.23007v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.23007v1}, note = {First published: 2026-03-24; Recorded arXiv version: v1; Recorded version updated: 2026-03-24T09:51:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.23791", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.23791"}} @misc{arxiv_2603_23791, title = {{The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense}}, author = {{Qianlong Lan} and {Anuj Kaul}}, year = {2026}, eprint = {2603.23791v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.23791v1}, note = {First published: 2026-03-24; Recorded arXiv version: v1; Recorded version updated: 2026-03-24T23:49:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.24157", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.24157"}} @misc{arxiv_2603_24157, title = {{CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare}}, author = {{Akash Ghosh} and {Tajamul Ashraf} and {Rishu Kumar Singh} and {Numan Saeed} and {Sriparna Saha} and {Xiuying Chen} and {Salman Khan}}, year = {2026}, eprint = {2603.24157v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.24157v1}, note = {First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T10:25:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.24440", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.24440"}} @misc{arxiv_2603_24440, title = {{CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents}}, author = {{Xiangru Jian} and {Shravan Nayak} and {Kevin Qinghong Lin} and {Aarash Feizi} and {Kaixin Li} and {Patrice Bechard} and {Spandana Gella} and {Sai Rajeswar}}, year = {2026}, eprint = {2603.24440v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.24440v1}, note = {First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T15:52:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.24533", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.24533"}} @misc{arxiv_2603_24533, title = {{UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience}}, author = {{Zichuan Lin} and {Feiyu Liu} and {Yijun Yang} and {Jiafei Lyu} and {Yiming Gao} and {Yicheng Liu} and {Zhicong Lu} and {Yangbin Yu} and {Mingyu Yang} and {Junyou Li} and {Deheng Ye} and {Jie Jiang}}, year = {2026}, eprint = {2603.24533v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.24533v1}, note = {First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T17:10:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.25226", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.25226"}} @misc{arxiv_2603_25226, title = {{WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing}}, author = {{Fanheng Kong} and {Jingyuan Zhang} and {Yang Yue} and {Chenxi Sun} and {Yang Tian} and {Shi Feng} and {Xiaocui Yang} and {Daling Wang} and {Yu Tian} and {Jun Du} and {Wenchong Zeng} and {Han Li} and {Kun Gai}}, year = {2026}, eprint = {2603.25226v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.25226v1}, note = {First published: 2026-03-26; Recorded arXiv version: v1; Recorded version updated: 2026-03-26T09:27:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.25864", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.25864"}} @misc{arxiv_2603_25864, title = {{GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks}}, author = {{Saelyne Yang} and {Jaesang Yu} and {Yi-Hao Peng} and {Kevin Qinghong Lin} and {Jae Won Cho} and {Yale Song} and {Juho Kim}}, year = {2026}, eprint = {2603.25864v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.25864v1}, note = {First published: 2026-03-26; Recorded arXiv version: v1; Recorded version updated: 2026-03-26T19:37:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.26041", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.26041"}} @misc{arxiv_2603_26041, title = {{Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation}}, author = {{Daiqiang Li} and {Zihao Pan} and {Zeyu Zhang} and {Xuyang Liu} and {Shijia Xu} and {Ronghao Chen} and {Huacan Wang} and {Honggang Chen} and {Linfeng Zhang} and {Zhangquan Chen} and {Haiyun Jiang}}, year = {2026}, eprint = {2603.26041v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.26041v4}, note = {First published: 2026-03-27; Recorded arXiv version: v4; Recorded version updated: 2026-08-09T16:37:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.26211", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.26211"}} @misc{arxiv_2603_26211, title = {{Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding}}, author = {{Shrinidhi Kumbhar} and {Haofu Liao} and {Srikar Appalaraju} and {Kunwar Yashraj Singh}}, year = {2026}, eprint = {2603.26211v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.26211v1}, note = {First published: 2026-03-27; Recorded arXiv version: v1; Recorded version updated: 2026-03-27T09:34:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.26266", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.26266"}} @misc{arxiv_2603_26266, title = {{GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation}}, author = {{Rui Xie} and {Zhi Gao} and {Chenrui Shi} and {Zirui Shang} and {Lu Chen} and {Qing Li}}, year = {2026}, eprint = {2603.26266v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.26266v3}, note = {First published: 2026-03-27; Recorded arXiv version: v3; Recorded version updated: 2026-06-30T04:47:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.28069", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2603.28069"}} @misc{arxiv_2603_28069, title = {{MolmoPoint: Better Pointing for VLMs with Grounding Tokens}}, author = {{Christopher Clark} and {Yue Yang} and {Jae Sung Park} and {Zixian Ma} and {Jieyu Zhang} and {Rohun Tripathi} and {Mohammadreza Salehi} and {Sangho Lee} and {Taira Anderson} and {Winson Han} and {Ranjay Krishna}}, year = {2026}, eprint = {2603.28069v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.28069v1}, note = {First published: 2026-03-30; Recorded arXiv version: v1; Recorded version updated: 2026-03-30T06:15:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.29020", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.29020"}} @misc{arxiv_2603_29020, title = {{Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild}}, author = {{Deepak Akkil} and {Mowafak Allaham} and {Amal Raj} and {Tamer Abuelsaad} and {Ravi Kokku}}, year = {2026}, eprint = {2603.29020v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.29020v1}, note = {First published: 2026-03-30; Recorded arXiv version: v1; Recorded version updated: 2026-03-30T21:27:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2603.29318", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.29318"}} @misc{arxiv_2603_29318, title = {{PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent}}, author = {{Hongyi Nie} and {Xunyuan Liu} and {Yudong Bai} and {Yaqing Wang} and {Yang Liu} and {Quanming Yao} and {Zhen Wang}}, year = {2026}, eprint = {2603.29318v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.29318v1}, note = {First published: 2026-03-31; Recorded arXiv version: v1; Recorded version updated: 2026-03-31T06:37:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.00886", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2604.00886"}} @misc{arxiv_2604_00886, title = {{PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding}}, author = {{Nan Wang} and {Zhiwei Jin} and {Chen Chen} and {Haonan Lu}}, year = {2026}, eprint = {2604.00886v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.00886v1}, note = {First published: 2026-04-01; Recorded arXiv version: v1; Recorded version updated: 2026-04-01T13:33:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.00986", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.00986"}} @misc{arxiv_2604_00986, title = {{Do Phone-Use Agents Respect Your Privacy?}}, author = {{Zhengyang Tang} and {Ke Ji} and {Xidong Wang} and {Zihan Ye} and {Xinyuan Wang} and {Yiduo Guo} and {Ziniu Li} and {Chenxin Li} and {Jingyuan Hu} and {Shunian Chen} and {Tongxu Luo} and {Jiaxi Bi} and {Zeyu Qin} and {Shaobo Wang} and {Xin Lai} and {Pengyuan Lyu} and {Junyi Li} and {Can Xu} and {Chengquan Zhang} and {Han Hu} and {Ming Yan} and {Benyou Wang}}, year = {2026}, eprint = {2604.00986v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.00986v2}, note = {First published: 2026-04-01; Recorded arXiv version: v2; Recorded version updated: 2026-04-02T13:51:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.01676", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.01676"}} @misc{arxiv_2604_01676, title = {{GPA: Learning GUI Process Automation from Demonstrations}}, author = {{Zirui Zhao} and {Jun Hao Liew} and {Yan Yang} and {Wenzhuo Yang} and {Ziyang Luo} and {Doyen Sahoo} and {Silvio Savarese} and {Junnan Li}}, year = {2026}, eprint = {2604.01676v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.01676v2}, note = {First published: 2026-04-02; Recorded arXiv version: v2; Recorded version updated: 2026-04-04T01:55:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.02345", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.02345"}} @misc{arxiv_2604_02345, title = {{UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics}}, author = {{Mengzhou Wu} and {Yuzhe Guo} and {Yuan Cao} and {Haochuan Lu} and {Songhe Zhu} and {Pingzhe Qu} and {Xin Chen} and {Kang Qin} and {Zhongpu Wang} and {Xiaode Zhang} and {Xinyi Wang} and {Wei Dai} and {Gang Cao} and {Yuetang Deng} and {Zhi Gong} and {Dezhi Ran} and {Linyi Li} and {Wei Yang} and {Tao Xie}}, year = {2026}, eprint = {2604.02345v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.02345v1}, note = {First published: 2026-02-11; Recorded arXiv version: v1; Recorded version updated: 2026-02-11T17:02:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.02623", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.02623"}} @misc{arxiv_2604_02623, title = {{Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents}}, author = {{Wei Zou} and {Mingwen Dong} and {Miguel Romero Calvo} and {Shuaichen Chang} and {Jiang Guo} and {Dongkyu Lee} and {Xing Niu} and {Xiaofei Ma} and {Yanjun Qi} and {Jiarong Jiang}}, year = {2026}, eprint = {2604.02623v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.02623v2}, note = {First published: 2026-04-03; Recorded arXiv version: v2; Recorded version updated: 2026-04-07T14:45:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.04399", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.04399"}} @misc{arxiv_2604_04399, title = {{GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis}}, author = {{Yuwen Zhai} and {Runze Li} and {Liang Wang} and {Nian Shi} and {Liwu Xu} and {Wei Zhang} and {Ran Lin} and {Bo Xu} and {Benlei Cui}}, year = {2026}, eprint = {2604.04399v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.04399v1}, note = {First published: 2026-04-06; Recorded arXiv version: v1; Recorded version updated: 2026-04-06T03:58:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.04918", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.04918"}} @misc{arxiv_2604_04918, title = {{Comparing Human Oversight Strategies for Computer-Use Agents}}, author = {{Chaoran Chen} and {Zhiping Zhang} and {Zeya Chen} and {Eryue Xu} and {Yinuo Yang} and {Ibrahim Khalilov} and {Simret A Gebreegziabher} and {Yanfang Ye} and {Ziang Xiao} and {Yaxing Yao} and {Tianshi Li} and {Toby Jia-Jun Li}}, year = {2026}, eprint = {2604.04918v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.04918v2}, note = {First published: 2026-04-06; Recorded arXiv version: v2; Recorded version updated: 2026-09-12T06:05:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.05157", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.05157"}} @misc{arxiv_2604_05157, title = {{IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents}}, author = {{Rongqian Chen} and {Yu Li} and {Zeyu Fang} and {Sizhe Tang} and {Weidong Cao} and {Tian Lan}}, year = {2026}, eprint = {2604.05157v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.05157v3}, note = {First published: 2026-04-06; Recorded arXiv version: v3; Recorded version updated: 2026-05-28T08:13:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.05477", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.05477"}} @misc{arxiv_2604_05477, title = {{Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction}}, author = {{Yuzhe Zhang} and {Xianwei Xue} and {Xingyong Wu} and {Mengke Chen} and {Chen Liu} and {Xinran He} and {Run Shao} and {Feiran Liu} and {Huanmin Xu} and {Qiutong Pan} and {Haiwei Wang}}, year = {2026}, eprint = {2604.05477v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.05477v1}, note = {First published: 2026-04-07; Recorded arXiv version: v1; Recorded version updated: 2026-04-07T06:16:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.06126", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.06126"}} @misc{arxiv_2604_06126, title = {{Gym-Anything: Turn any Software into an Agent Environment}}, author = {{Pranjal Aggarwal} and {Graham Neubig} and {Sean Welleck}}, year = {2026}, eprint = {2604.06126v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.06126v1}, note = {First published: 2026-04-07; Recorded arXiv version: v1; Recorded version updated: 2026-04-07T17:38:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.06240", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.06240"}} @misc{arxiv_2604_06240, title = {{The Art of Building Verifiers for Computer Use Agents}}, author = {{Corby Rosset} and {Pratyusha Sharma} and {Andrew Zhao} and {Miguel Gonzalez-Fernandez} and {Ahmed Awadallah}}, year = {2026}, eprint = {2604.06240v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.06240v1}, note = {First published: 2026-04-05; Recorded arXiv version: v1; Recorded version updated: 2026-04-05T06:26:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.06367", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.06367"}} @misc{arxiv_2604_06367, title = {{WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks}}, author = {{Guruprasad Viswanathan Ramesh} and {Asmit Nayak} and {Basieem Siddique} and {Kassem Fawaz}}, year = {2026}, eprint = {2604.06367v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.06367v2}, note = {First published: 2026-04-07; Recorded arXiv version: v2; Recorded version updated: 2026-06-16T22:37:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.06995", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.06995"}} @misc{arxiv_2604_06995, title = {{What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning}}, author = {{Songze Li} and {Xiaoke Guo} and {Tianqi Liu} and {Biao Yi} and {Zhaoyan Gong} and {Zhiqiang Liu} and {Huajun Chen} and {Wen Zhang}}, year = {2026}, eprint = {2604.06995v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.06995v3}, note = {First published: 2026-04-08; Recorded arXiv version: v3; Recorded version updated: 2026-10-02T06:30:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.07277", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.07277"}} @misc{arxiv_2604_07277, title = {{Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions}}, author = {{Guo Gan} and {Yuxuan Ding} and {Cong Chen} and {Yuwei Ren} and {Yin Huang} and {Hong Zhou}}, year = {2026}, eprint = {2604.07277v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.07277v2}, note = {First published: 2026-04-08; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T03:06:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.07831", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.07831"}} @misc{arxiv_2604_07831, title = {{Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection}}, author = {{Wenkui Yang} and {Chao Jin} and {Haisu Zhu} and {Weilin Luo} and {Derek Yuen} and {Kun Shao} and {Junxian Duan} and {Huaibo Huang} and {Jie Cao} and {Ran He}}, year = {2026}, eprint = {2604.07831v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.07831v2}, note = {First published: 2026-04-09; Recorded arXiv version: v2; Recorded version updated: 2026-07-08T02:39:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.08516", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.08516"}} @misc{arxiv_2604_08516, title = {{MolmoWeb: Open Visual Web Agent and Open Data for the Open Web}}, author = {{Tanmay Gupta} and {Piper Wolters} and {Zixian Ma} and {Peter Sushko} and {Rock Yuren Pang} and {Diego Llanes} and {Yue Yang} and {Taira Anderson} and {Boyuan Zheng} and {Zhongzheng Ren} and {Harsh Trivedi} and {Taylor Blanton} and {Caleb Ouellette} and {Winson Han} and {Ali Farhadi} and {Ranjay Krishna}}, year = {2026}, eprint = {2604.08516v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.08516v1}, note = {First published: 2026-04-09; Recorded arXiv version: v1; Recorded version updated: 2026-04-09T17:54:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.09155", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.09155"}} @misc{arxiv_2604_09155, title = {{CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation}}, author = {{Yushi Feng} and {Junye Du} and {Qifan Wang} and {Zizhan Ma} and {Qian Niu} and {Yutaka Matsuo} and {Long Feng} and {Lequan Yu}}, year = {2026}, eprint = {2604.09155v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.09155v1}, note = {First published: 2026-04-10; Recorded arXiv version: v1; Recorded version updated: 2026-04-10T09:41:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.09581", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.09581"}} @misc{arxiv_2604_09581, title = {{Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding}}, author = {{Wee Joe Tan} and {Zi Rui Lucas Lim} and {Shashank Durgad} and {Karim Obegi} and {Aiden Yiliu Li}}, year = {2026}, eprint = {2604.09581v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.09581v2}, note = {First published: 2026-02-25; Recorded arXiv version: v2; Recorded version updated: 2026-04-14T20:54:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.09815", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.09815"}} @misc{arxiv_2604_09815, title = {{EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning}}, author = {{Tiantian He} and {Yihang Chen} and {Keyue Jiang} and {Ka Yiu Lee} and {Kaiwen Zhou} and {Kun Shao} and {Shuai Wang}}, year = {2026}, eprint = {2604.09815v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.09815v1}, note = {First published: 2026-04-10; Recorded arXiv version: v1; Recorded version updated: 2026-04-10T18:46:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.09937", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.09937"}} @misc{arxiv_2604_09937, title = {{HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks}}, author = {{Suhana Bedi} and {Ryan Welch} and {Ethan Steinberg} and {Michael Wornow} and {Taeil Matthew Kim} and {Haroun Ahmed} and {Peter Sterling} and {Bravim Purohit} and {Qurat Akram} and {Angelic Acosta} and {Esther Nubla} and {Pritika Sharma} and {Michael A. Pfeffer} and {Sanmi Koyejo} and {Nigam H. Shah}}, year = {2026}, eprint = {2604.09937v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.09937v1}, note = {First published: 2026-04-10; Recorded arXiv version: v1; Recorded version updated: 2026-04-10T22:33:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.10988", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.10988"}} @misc{arxiv_2604_10988, title = {{WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark}}, author = {{Peng Yuan} and {Yuyang Yin} and {Yuxuan Cai} and {Zheng Wei}}, year = {2026}, eprint = {2604.10988v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.10988v1}, note = {First published: 2026-04-13; Recorded arXiv version: v1; Recorded version updated: 2026-04-13T04:45:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.11784", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.11784"}} @misc{arxiv_2604_11784, title = {{ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents}}, author = {{Fei Tang} and {Zhiqiong Lu} and {Boxuan Zhang} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang} and {Yongliang Shen}}, year = {2026}, eprint = {2604.11784v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.11784v1}, note = {First published: 2026-04-13; Recorded arXiv version: v1; Recorded version updated: 2026-04-13T17:52:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.12284", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.12284"}} @misc{arxiv_2604_12284, title = {{WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents}}, author = {{Yulin Chen} and {Tri Cao} and {Haoran Li} and {Yue Liu} and {Yibo Li} and {Yufei He} and {Le Minh Khoi} and {Yangqiu Song} and {Shuicheng Yan} and {Bryan Hooi}}, year = {2026}, eprint = {2604.12284v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.12284v1}, note = {First published: 2026-04-14; Recorded arXiv version: v1; Recorded version updated: 2026-04-14T04:50:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.13019", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.13019"}} @misc{arxiv_2604_13019, title = {{PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors}}, author = {{Himangi Mittal} and {Gaurav Mittal} and {Nelson Daniel Troncoso} and {Yu Hu}}, year = {2026}, eprint = {2604.13019v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.13019v3}, note = {First published: 2026-04-14; Recorded arXiv version: v3; Recorded version updated: 2026-05-28T06:47:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.13318", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.13318"}} @misc{arxiv_2604_13318, title = {{WebXSkill: Skill Learning for Autonomous Web Agents}}, author = {{Zhaoyang Wang} and {Qianhui Wu} and {Xuchao Zhang} and {Chaoyun Zhang} and {Wenlin Yao} and {Fazle Elahi Faisal} and {Baolin Peng} and {Si Qin} and {Suman Nath} and {Qingwei Lin} and {Chetan Bansal} and {Dongmei Zhang} and {Saravan Rajmohan} and {Jianfeng Gao} and {Huaxiu Yao}}, year = {2026}, eprint = {2604.13318v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.13318v2}, note = {First published: 2026-04-14; Recorded arXiv version: v2; Recorded version updated: 2026-08-31T07:02:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.13822", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.13822"}} @misc{arxiv_2604_13822, title = {{UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization}}, author = {{Zhengxi Lu} and {Fei Tang} and {Guangyi Liu} and {Kaitao Song} and {Xu Tan} and {Jin Ma} and {Wenqi Zhang} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang} and {Yongliang Shen}}, year = {2026}, eprint = {2604.13822v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.13822v1}, note = {First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T12:55:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.14113", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.14113"}} @misc{arxiv_2604_14113, title = {{UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding}}, author = {{Fei Tang} and {Bofan Chen} and {Zhengxi Lu} and {Tongbo Chen} and {Songqin Nong} and {Tao Jiang} and {Wenhao Xu} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang} and {Yongliang Shen}}, year = {2026}, eprint = {2604.14113v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.14113v1}, note = {First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T17:32:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.14262", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.14262"}} @misc{arxiv_2604_14262, title = {{GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models}}, author = {{Yangyue Wang} and {Harshvardhan Sikka} and {Yash Mathur} and {Tony Zhou} and {Jinu Nyachhyon} and {Pranav Guruprasad}}, year = {2026}, eprint = {2604.14262v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.14262v2}, note = {First published: 2026-04-15; Recorded arXiv version: v2; Recorded version updated: 2026-07-01T10:12:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.14668", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.14668"}} @misc{arxiv_2604_14668, title = {{Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation}}, author = {{Pan Hao} and {Rishi Selvakumaran} and {Jacob Sun} and {Qianwen Wang}}, year = {2026}, eprint = {2604.14668v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.14668v1}, note = {First published: 2026-04-16; Recorded arXiv version: v1; Recorded version updated: 2026-04-16T06:22:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.14956", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.14956"}} @misc{arxiv_2604_14956, title = {{FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems}}, author = {{Wenhao Wang} and {Haoting Shi} and {Mengying Yuan} and {Yiquan Lin} and {Panrong Tong} and {Hanzhang Zhou} and {Guangyi Liu} and {Pengxiang Zhao} and {Yue Wang} and {Siheng Chen}}, year = {2026}, eprint = {2604.14956v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.14956v1}, note = {First published: 2026-04-16; Recorded arXiv version: v1; Recorded version updated: 2026-04-16T12:53:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.15093", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.15093"}} @misc{arxiv_2604_15093, title = {{OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis}}, author = {{Kanzhi Cheng} and {Zehao Li} and {Zheng Ma} and {Nuo Chen} and {Jialin Cao} and {Qiushi Sun} and {Zichen Ding} and {Fangzhi Xu} and {Hang Yan} and {Jiajun Chen} and {Anh Tuan Luu} and {Jianbing Zhang} and {Lewei Lu} and {Dahua Lin}}, year = {2026}, eprint = {2604.15093v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.15093v1}, note = {First published: 2026-04-16; Recorded arXiv version: v1; Recorded version updated: 2026-04-16T14:53:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.16515", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.16515"}} @misc{arxiv_2604_16515, title = {{Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations}}, author = {{Jiachen Qian} and {Zhaolu Kang}}, year = {2026}, eprint = {2604.16515v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.16515v1}, note = {First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T10:46:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.16520", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2604.16520"}} @misc{arxiv_2604_16520, title = {{AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents}}, author = {{Haomin Zhuang} and {Hanwen Xing} and {Xiangliang Zhang}}, year = {2026}, eprint = {2604.16520v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.16520v1}, note = {First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T18:22:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.16548", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2604.16548"}} @misc{arxiv_2604_16548, title = {{A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle}}, author = {{Zehao Lin} and {Xixuan Hao} and {Renyu Fu} and {Shaobo Cui} and {Kai Chen} and {Chunyu Li} and {Zhiyu Li} and {Feiyu Xiong}}, year = {2026}, eprint = {2604.16548v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.16548v3}, note = {First published: 2026-04-17; Recorded arXiv version: v3; Recorded version updated: 2026-09-22T07:33:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.17284", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.17284"}} @misc{arxiv_2604_17284, title = {{HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents}}, author = {{Chao Jin} and {Wenkui Yang} and {Hao Sun} and {Yuqi Liao} and {Qianyi Jiang} and {Kai Zhou} and {Jie Cao} and {Ran He} and {Huaibo Huang}}, year = {2026}, eprint = {2604.17284v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.17284v1}, note = {First published: 2026-04-19; Recorded arXiv version: v1; Recorded version updated: 2026-04-19T06:55:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.17817", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.17817"}} @misc{arxiv_2604_17817, title = {{Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots}}, author = {{Shiquan Zhang} and {Tianyi Zhang} and {Le Fang} and {Simon D'Alfonso} and {Hong Jia} and {Vassilis Kostakos}}, year = {2026}, eprint = {2604.17817v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.17817v1}, note = {First published: 2026-04-20; Recorded arXiv version: v1; Recorded version updated: 2026-04-20T05:15:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.17821", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.17821"}} @misc{arxiv_2604_17821, title = {{WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent}}, author = {{Lingfeng Zhang} and {Yongan Sun} and {Jinpeng Hu} and {Hui Ma} and {Yang Ying} and {Kuien Liu} and {Zenglin Shi} and {Meng Wang}}, year = {2026}, eprint = {2604.17821v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.17821v2}, note = {First published: 2026-04-20; Recorded arXiv version: v2; Recorded version updated: 2026-04-21T03:15:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.17849", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.17849"}} @misc{arxiv_2604_17849, title = {{On the Reliability of Computer Use Agents}}, author = {{Gonzalo Gonzalez-Pumariega} and {Saaket Agashe} and {Jiachen Yang} and {Ang Li} and {Xin Eric Wang}}, year = {2026}, eprint = {2604.17849v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.17849v1}, note = {First published: 2026-04-20; Recorded arXiv version: v1; Recorded version updated: 2026-04-20T05:59:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.18240", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.18240"}} @misc{arxiv_2604_18240, title = {{AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation}}, author = {{Wentao Shi} and {Yu Wang} and {Yuyang Zhao} and {Yuxin Chen} and {Fuli Feng} and {Xueyuan Hao} and {Xi Su} and {Qi Gu} and {Hui Su} and {Xunliang Cai} and {Xiangnan He}}, year = {2026}, eprint = {2604.18240v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.18240v1}, note = {First published: 2026-04-20; Recorded arXiv version: v1; Recorded version updated: 2026-04-20T13:23:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.18860", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.18860"}} @misc{arxiv_2604_18860, title = {{Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents}}, author = {{Wenpeng Xu}}, year = {2026}, eprint = {2604.18860v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.18860v1}, note = {First published: 2026-04-20; Recorded arXiv version: v1; Recorded version updated: 2026-04-20T21:36:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.19742", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.19742"}} @misc{arxiv_2604_19742, title = {{PlayCoder: Making LLM-Generated GUI Code Playable}}, author = {{Zhiyuan Peng} and {Wei Tao} and {Xin Yin} and {Chenhao Ying} and {Yuan Luo} and {Yiwen Guo}}, year = {2026}, eprint = {2604.19742v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.19742v2}, note = {First published: 2026-04-21; Recorded arXiv version: v2; Recorded version updated: 2026-09-29T10:11:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.21268", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.21268"}} @misc{arxiv_2604_21268, title = {{Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding}}, author = {{Wenkai Wang} and {Xiyun Li} and {Hongcan Guo} and {Wenhao Yu} and {Tianqing Fang} and {Haitao Mi} and {Dong Yu} and {Shengyu Zhang}}, year = {2026}, eprint = {2604.21268v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.21268v1}, note = {First published: 2026-04-23; Recorded arXiv version: v1; Recorded version updated: 2026-04-23T04:23:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.21375", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.21375"}} @misc{arxiv_2604_21375, title = {{VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation}}, author = {{Qijun Han} and {Haoqin Tu} and {Zijun Wang} and {Haoyue Dai} and {Yiyang Zhou} and {Nancy Lau} and {Alvaro A. Cardenas} and {Yuhui Xu} and {Ran Xu} and {Caiming Xiong} and {Zeyu Zheng} and {Huaxiu Yao} and {Yuyin Zhou} and {Cihang Xie}}, year = {2026}, eprint = {2604.21375v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.21375v3}, note = {First published: 2026-04-23; Recorded arXiv version: v3; Recorded version updated: 2026-09-24T23:58:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.23941", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.23941"}} @misc{arxiv_2604_23941, title = {{GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction}}, author = {{Hongxin Li} and {Yuntao Chen} and {Zhaoxiang Zhang}}, year = {2026}, eprint = {2604.23941v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.23941v1}, note = {First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T01:29:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.24348", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.24348"}} @misc{arxiv_2604_24348, title = {{OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents}}, author = {{Zheng Wu} and {Yi Hua} and {Zhaoyuan Huang} and {Chenhao Xue} and {Yijie Lu} and {Pengzhou Cheng} and {Zongru Wu} and {Lingzhong Dong} and {Gongshen Liu} and {Xinghao Jiang} and {Zhuosheng Zhang}}, year = {2026}, eprint = {2604.24348v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.24348v1}, note = {First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T11:44:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.24441", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.24441"}} @misc{arxiv_2604_24441, title = {{AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark}}, author = {{Hongxin Li} and {Xiping Wang} and {Jingran Su} and {Zheng Ju} and {Yuntao Chen} and {Qing Li} and {Zhaoxiang Zhang}}, year = {2026}, eprint = {2604.24441v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.24441v1}, note = {First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T13:06:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.24964", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.24964"}} @misc{arxiv_2604_24964, title = {{Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks}}, author = {{Lawrence Keunho Jang} and {Jing Yu Koh} and {Daniel Fried} and {Ruslan Salakhutdinov}}, year = {2026}, eprint = {2604.24964v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.24964v1}, note = {First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T20:05:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.25380", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.25380"}} @misc{arxiv_2604_25380, title = {{Benchmarking and Improving GUI Agents in High-Dynamic Environments}}, author = {{Enqi Liu} and {Liyuan Pan} and {Zhi Gao} and {Yan Yang} and {Chenrui Shi} and {Yang Liu} and {Jingrong Wu} and {Qing Li}}, year = {2026}, eprint = {2604.25380v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.25380v2}, note = {First published: 2026-04-28; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T04:29:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.25562", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.25562"}} @misc{arxiv_2604_25562, title = {{SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents}}, author = {{Mengyao Du} and {Han Fang} and {Haokai Ma} and {Jiahao Chen} and {Kai Xu} and {Quanjun Yin} and {Ee-Chien Chang}}, year = {2026}, eprint = {2604.25562v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.25562v1}, note = {First published: 2026-04-28; Recorded arXiv version: v1; Recorded version updated: 2026-04-28T12:32:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.26020", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.26020"}} @misc{arxiv_2604_26020, title = {{Training Computer Use Agents to Assess the Usability of Graphical User Interfaces}}, author = {{Alice Gao} and {Weixi Tong} and {Rishab Vempati} and {Katharina Reinecke} and {R. Benjamin Shapiro} and {Tianyi Zhang} and {Jason Wu}}, year = {2026}, eprint = {2604.26020v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.26020v1}, note = {First published: 2026-04-28; Recorded arXiv version: v1; Recorded version updated: 2026-04-28T18:04:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.26148", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.26148"}} @misc{arxiv_2604_26148, title = {{Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations}}, author = {{Chen Liang} and {Xirui Jiang} and {Naihao Deng} and {Eytan Adar} and {Anhong Guo}}, year = {2026}, eprint = {2604.26148v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.26148v3}, note = {First published: 2026-04-28; Recorded arXiv version: v3; Recorded version updated: 2026-08-11T15:48:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.27151", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.27151"}} @misc{arxiv_2604_27151, title = {{Step-level Optimization for Efficient Computer-use Agents}}, author = {{Jinbiao Wei} and {Kangqi Ni} and {Yilun Zhao} and {Guo Gan} and {Arman Cohan}}, year = {2026}, eprint = {2604.27151v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.27151v1}, note = {First published: 2026-04-29; Recorded arXiv version: v1; Recorded version updated: 2026-04-29T19:59:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.27253", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.27253"}} @misc{arxiv_2604_27253, title = {{AutoSurfer -- Teaching Web Agents through Comprehensive Surfing, Learning, and Modeling}}, author = {{Fazle Elahi Faisal} and {Qianhui Wu} and {Baolin Peng} and {Jianfeng Gao}}, year = {2026}, eprint = {2604.27253v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.27253v1}, note = {First published: 2026-04-29; Recorded arXiv version: v1; Recorded version updated: 2026-04-29T22:57:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.27776", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.27776"}} @misc{arxiv_2604_27776, title = {{WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments}}, author = {{Jinchao Li} and {Yunxin Li} and {Chenrui Zhao} and {Zhenran Xu} and {Baotian Hu} and {Min Zhang}}, year = {2026}, eprint = {2604.27776v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.27776v1}, note = {First published: 2026-04-30; Recorded arXiv version: v1; Recorded version updated: 2026-04-30T12:13:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2604.27996", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.27996"}} @misc{arxiv_2604_27996, title = {{Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization}}, author = {{Jackson Vonderhorst} and {Kuangshi Ai} and {Haichao Miao} and {Shusen Liu} and {Chaoli Wang}}, year = {2026}, eprint = {2604.27996v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.27996v3}, note = {First published: 2026-04-30; Recorded arXiv version: v3; Recorded version updated: 2026-06-26T20:31:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.00551", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.00551"}} @misc{arxiv_2605_00551, title = {{A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction}}, author = {{Michito Takeshita} and {Takuro Kawada} and {Takumi Ohashi} and {Shunsuke Kitada} and {Hitoshi Iyatomi}}, year = {2026}, eprint = {2605.00551v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.00551v1}, note = {First published: 2026-05-01; Recorded arXiv version: v1; Recorded version updated: 2026-05-01T10:16:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.01208", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.01208"}} @misc{arxiv_2605_01208, title = {{Faithful Mobile GUI Agents with Guided Advantage Estimator}}, author = {{Haowen Hu} and {Pengzhou Cheng} and {Zheng Wu} and {Lingzhong Dong} and {Gongshen Liu} and {Zhuosheng Zhang}}, year = {2026}, eprint = {2605.01208v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.01208v1}, note = {First published: 2026-05-02; Recorded arXiv version: v1; Recorded version updated: 2026-05-02T02:54:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.02630", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.02630"}} @misc{arxiv_2605_02630, title = {{AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding}}, author = {{Ruilin Yao} and {Shegnwu Xiong} and {Tianyu Zou} and {Shili Xiong} and {Yi Rong}}, year = {2026}, eprint = {2605.02630v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.02630v1}, note = {First published: 2026-05-04; Recorded arXiv version: v1; Recorded version updated: 2026-05-04T14:18:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.05509", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.05509"}} @misc{arxiv_2605_05509, title = {{WAAA! Web Adversaries Against Agentic Browsers}}, author = {{Sohom Datta} and {Alex Nahapetyan} and {William Enck} and {Alexandros Kapravelos}}, year = {2026}, eprint = {2605.05509v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.05509v1}, note = {First published: 2026-05-06; Recorded arXiv version: v1; Recorded version updated: 2026-05-06T23:19:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.05765", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.05765"}} @misc{arxiv_2605_05765, title = {{X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction}}, author = {{Xiaoming Ren} and {Ru Zhen} and {Chao Li} and {Yang Song} and {Qiuxia Hou} and {Yanhao Zhang} and {Peng Liu} and {Qi Qi} and {Quanlong Zheng} and {Qi Wu} and {Zhenyi Liao} and {Binqiang Pan} and {Haobo Ji} and {Haonan Lu}}, year = {2026}, eprint = {2605.05765v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.05765v2}, note = {First published: 2026-05-07; Recorded arXiv version: v2; Recorded version updated: 2026-05-21T06:55:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.06761", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.06761"}} @misc{arxiv_2605_06761, title = {{Weblica: Scalable and Reproducible Training Environments for Visual Web Agents}}, author = {{Oğuzhan Fatih Kar} and {Roman Bachmann} and {Yuanzheng Gong} and {Anders Boesen Lindbo Larsen} and {Afshin Dehghan}}, year = {2026}, eprint = {2605.06761v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.06761v1}, note = {First published: 2026-05-07; Recorded arXiv version: v1; Recorded version updated: 2026-05-07T17:17:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.07134", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.07134"}} @misc{arxiv_2605_07134, title = {{Region4Web: Rethinking Observation Space Granularity for Web Agents}}, author = {{Donguk Kwon} and {Dongha Lee}}, year = {2026}, eprint = {2605.07134v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.07134v1}, note = {First published: 2026-05-08; Recorded arXiv version: v1; Recorded version updated: 2026-05-08T02:11:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.09317", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.09317"}} @misc{arxiv_2605_09317, title = {{Mem-W: Latent Memory-Native GUI Agents}}, author = {{Guibin Zhang} and {Yaohui Ling} and {Fanci Meng} and {Kun Wang} and {Shuicheng Yan}}, year = {2026}, eprint = {2605.09317v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.09317v1}, note = {First published: 2026-05-10; Recorded arXiv version: v1; Recorded version updated: 2026-05-10T04:31:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.09497", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.09497"}} @misc{arxiv_2605_09497, title = {{Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces}}, author = {{Yilin Zhang} and {Yingkai Hua} and {Chunyu Wei} and {Xin Wang} and {Yueguo Chen}}, year = {2026}, eprint = {2605.09497v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.09497v1}, note = {First published: 2026-05-10; Recorded arXiv version: v1; Recorded version updated: 2026-05-10T12:11:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.10347", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.10347"}} @misc{arxiv_2605_10347, title = {{How Mobile World Model Guides GUI Agents?}}, author = {{Weikai Xu} and {Kun Huang} and {Yunren Feng} and {Jiaxing Li} and {Yuhan Chen} and {Yuxuan Liu} and {Zhizheng Jiang} and {Heng Qu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Xiaolin Hu} and {Bo An}}, year = {2026}, eprint = {2605.10347v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.10347v2}, note = {First published: 2026-05-11; Recorded arXiv version: v2; Recorded version updated: 2026-05-22T05:43:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.10966", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2605.10966"}} @misc{arxiv_2605_10966, title = {{MMTB: Evaluating Terminal Agents on Multimedia-File Tasks}}, author = {{Chiyeong Heo} and {Jaechang Kim} and {Junhyuk Kwon} and {Hoyoung Kim} and {Dongmin Park} and {Jonghyun Lee} and {Jungseul Ok}}, year = {2026}, eprint = {2605.10966v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.10966v1}, note = {First published: 2026-05-08; Recorded arXiv version: v1; Recorded version updated: 2026-05-08T10:57:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.11212", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.11212"}} @misc{arxiv_2605_11212, title = {{ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction}}, author = {{Amirhossein Abaskohi} and {Yuhang He} and {Peter West} and {Giuseppe Carenini} and {Pranit Chawla} and {Vibhav Vineet}}, year = {2026}, eprint = {2605.11212v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.11212v3}, note = {First published: 2026-05-11; Recorded arXiv version: v3; Recorded version updated: 2026-06-05T22:18:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.12294", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.12294"}} @misc{arxiv_2605_12294, title = {{Executable Agentic Memory for GUI Agent}}, author = {{Zerui Qin} and {Sheng Yue} and {Xingyuan Hua} and {Yongjian Fu} and {Ju Ren}}, year = {2026}, eprint = {2605.12294v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12294v1}, note = {First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T15:48:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.12481", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.12481"}} @misc{arxiv_2605_12481, title = {{ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents}}, author = {{Xuhao Hu} and {Xi Zhang} and {Haiyang Xu} and {Kyle Qiao} and {Jingyi Yang} and {Xuanjing Huang} and {Jing Shao} and {Ming Yan} and {Jieping Ye}}, year = {2026}, eprint = {2605.12481v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12481v2}, note = {First published: 2026-05-12; Recorded arXiv version: v2; Recorded version updated: 2026-09-19T14:53:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.12493", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.12493"}} @misc{arxiv_2605_12493, title = {{LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues}}, author = {{Di Wu} and {Zixiang Ji} and {Asmi Kawatkar} and {Bryan Kwan} and {Jia-Chen Gu} and {Nanyun Peng} and {Kai-Wei Chang}}, year = {2026}, eprint = {2605.12493v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12493v1}, note = {First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T17:59:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.12501", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.12501"}} @misc{arxiv_2605_12501, title = {{Covering Human Action Space for Computer Use: Data Synthesis and Benchmark}}, author = {{Miaosen Zhang} and {Xiaohan Zhao} and {Zhihong Tan} and {Zhou Huoshen} and {Yijia Fan} and {Yifan Yang} and {Kai Qiu} and {Bei Liu} and {Justin Wagle} and {Chenzhong Yin} and {Mingxi Cheng} and {Ji Li} and {Qi Dai} and {Chong Luo} and {Xu Yang} and {Xin Geng} and {Baining Guo}}, year = {2026}, eprint = {2605.12501v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12501v1}, note = {First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T17:59:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.12549", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.12549"}} @misc{arxiv_2605_12549, title = {{What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs}}, author = {{Jiaping Lin} and {Fei Shen} and {Junzhe Li} and {Ping Nie} and {Fei Yu} and {Ming Li} and {Haizhou Li}}, year = {2026}, eprint = {2605.12549v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12549v1}, note = {First published: 2026-05-10; Recorded arXiv version: v1; Recorded version updated: 2026-05-10T07:04:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.14290", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2605.14290"}} @misc{arxiv_2605_14290, title = {{Web Agents Should Adopt the Plan-Then-Execute Paradigm}}, author = {{Julien Piet} and {Annabella Chow} and {Yiwei Hou} and {Muxi Lyu} and {Sylvie Venuto} and {Jinhao Zhu} and {Raluca Ada Popa} and {David Wagner}}, year = {2026}, eprint = {2605.14290v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.14290v1}, note = {First published: 2026-05-14; Recorded arXiv version: v1; Recorded version updated: 2026-05-14T02:48:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.15542", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.15542"}} @misc{arxiv_2605_15542, title = {{DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding}}, author = {{Yichao Liu} and {Huawen Shen} and {Liu Yu} and {Shiyu Liu} and {Zeyu Chen} and {Yu Zhou}}, year = {2026}, eprint = {2605.15542v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.15542v1}, note = {First published: 2026-05-15; Recorded arXiv version: v1; Recorded version updated: 2026-05-15T02:27:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.15777", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.15777"}} @misc{arxiv_2605_15777, title = {{SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?}}, author = {{Kean Shi} and {Zihang Li} and {Tianyi Ma} and {Zengji Tu} and {Jialong Wu} and {Xinbo Xu} and {Qingyao Yang} and {Ruoyu Wu} and {Weichu Xie} and {Ming Wu} and {Jason Zeng} and {Michael Heinrich} and {Elvis Zhang} and {Liang Chen} and {Kuan Li} and {Baobao Chang}}, year = {2026}, eprint = {2605.15777v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.15777v2}, note = {First published: 2026-05-15; Recorded arXiv version: v2; Recorded version updated: 2026-05-24T16:35:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.16402", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.16402"}} @misc{arxiv_2605_16402, title = {{WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments}}, author = {{Haoren Zhao} and {Tianyi Chen} and {Zhen Wang}}, year = {2026}, eprint = {2605.16402v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.16402v1}, note = {First published: 2026-05-13; Recorded arXiv version: v1; Recorded version updated: 2026-05-13T02:48:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.16883", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.16883"}} @misc{arxiv_2605_16883, title = {{SE-GA: Memory-Augmented Self-Evolution for GUI Agents}}, author = {{Shilong Jin} and {Lanjun Wang} and {Zhuosheng Zhang}}, year = {2026}, eprint = {2605.16883v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.16883v1}, note = {First published: 2026-05-16; Recorded arXiv version: v1; Recorded version updated: 2026-05-16T08:51:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.17320", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.17320"}} @misc{arxiv_2605_17320, title = {{TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents}}, author = {{Yutong Huang} and {Vikranth Srivatsa} and {Alex Asch} and {Hansin Tushar Patwa} and {Yiying Zhang}}, year = {2026}, eprint = {2605.17320v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.17320v1}, note = {First published: 2026-05-17; Recorded arXiv version: v1; Recorded version updated: 2026-05-17T08:24:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.17656", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.17656"}} @misc{arxiv_2605_17656, title = {{MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding}}, author = {{Athar Parvez} and {Muhammad Jawad Mufti} and {Muqaddas Gull} and {Omar Hammad}}, year = {2026}, eprint = {2605.17656v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.17656v1}, note = {First published: 2026-05-17; Recorded arXiv version: v1; Recorded version updated: 2026-05-17T21:14:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.18048", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.18048"}} @misc{arxiv_2605_18048, title = {{DocOS: Towards Proactive Document-Guided Actions in GUI Agents}}, author = {{Jingjing Liu} and {Ziye Huang} and {Zihao Cheng} and {Zeming Liu} and {Jiahong Wu} and {Yuhang Guo} and {Kehai Chen} and {Yunhong Wang} and {Haifeng Wang}}, year = {2026}, eprint = {2605.18048v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.18048v1}, note = {First published: 2026-05-18; Recorded arXiv version: v1; Recorded version updated: 2026-05-18T08:36:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.18652", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.18652"}} @misc{arxiv_2605_18652, title = {{MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents}}, author = {{Ziyun Zeng} and {Hang Hua} and {Bocheng Zou} and {Mu Cai} and {Rogerio Feris} and {Jiebo Luo}}, year = {2026}, eprint = {2605.18652v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.18652v1}, note = {First published: 2026-05-18; Recorded arXiv version: v1; Recorded version updated: 2026-05-18T16:57:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.18758", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.18758"}} @misc{arxiv_2605_18758, title = {{OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments}}, author = {{Felix Henry} and {Lihan Lin} and {Jiangyou Zhu} and {Yangfan} and {Bingqian Zhang} and {Min Chen} and {Shiyu Huang}}, year = {2026}, eprint = {2605.18758v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.18758v2}, note = {First published: 2026-04-03; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T02:42:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.19769", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.19769"}} @misc{arxiv_2605_19769, title = {{OpenComputer: Verifiable Software Worlds for Computer-Use Agents}}, author = {{Jinbiao Wei} and {Qianran Ma} and {Yilun Zhao} and {Xiao Zhou} and {Kangqi Ni} and {Guo Gan} and {Arman Cohan}}, year = {2026}, eprint = {2605.19769v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.19769v1}, note = {First published: 2026-05-19; Recorded arXiv version: v1; Recorded version updated: 2026-05-19T12:40:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.20291", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.20291"}} @misc{arxiv_2605_20291, title = {{Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection}}, author = {{Fatemeh Pesaran Zadeh} and {Seyeon Choi} and {Xing Han Lù} and {Siva Reddy} and {Gunhee Kim}}, year = {2026}, eprint = {2605.20291v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.20291v2}, note = {First published: 2026-05-19; Recorded arXiv version: v2; Recorded version updated: 2026-05-26T02:53:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.21470", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.21470"}} @misc{arxiv_2605_21470, title = {{Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling}}, author = {{Caleb Winston} and {Ron Yifeng Wang} and {Azalia Mirhoseini} and {Christos Kozyrakis}}, year = {2026}, eprint = {2605.21470v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.21470v2}, note = {First published: 2026-05-20; Recorded arXiv version: v2; Recorded version updated: 2026-05-29T17:54:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.24785", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.24785"}} @misc{arxiv_2605_24785, title = {{PANDO: Efficient Multimodal AI Agents via Online Skill Distillation}}, author = {{Yubo Li} and {Yidi Miao} and {Yuntian Shen} and {Yuxin Liu}}, year = {2026}, eprint = {2605.24785v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.24785v2}, note = {First published: 2026-05-24; Recorded arXiv version: v2; Recorded version updated: 2026-05-26T04:25:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.25160", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.25160"}} @misc{arxiv_2605_25160, title = {{ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis}}, author = {{Guohong Liu} and {Jialei Ye} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Yunxin Liu} and {Yuanchun Li}}, year = {2026}, eprint = {2605.25160v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.25160v2}, note = {First published: 2026-05-24; Recorded arXiv version: v2; Recorded version updated: 2026-06-18T02:24:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.25624", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.25624"}} @misc{arxiv_2605_25624, title = {{CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents}}, author = {{Bowen Wang} and {Dunjie Lu} and {Junli Wang} and {Tianyi Bai} and {Shixuan Liu} and {Zhipeng Zhang} and {Haiquan Wang} and {Hao Hu} and {Tianbao Xie} and {Shuai Bai} and {Dayiheng Liu} and {Que Shen} and {Junyang Lin} and {Tao Yu}}, year = {2026}, eprint = {2605.25624v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.25624v2}, note = {First published: 2026-05-25; Recorded arXiv version: v2; Recorded version updated: 2026-06-08T08:32:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.26086", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.26086"}} @misc{arxiv_2605_26086, title = {{Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World}}, author = {{Yusong Lin} and {Xinyuan Liang} and {Haiyang Wang} and {Qipeng Gu} and {Siqi Cheng} and {Jiangui Chen} and {Shuzhe Wu} and {Feiyang Pan} and {Lue Fan} and {Sanyuan Zhao} and {Dandan Tu}}, year = {2026}, eprint = {2605.26086v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.26086v1}, note = {First published: 2026-05-25; Recorded arXiv version: v1; Recorded version updated: 2026-05-25T17:50:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.26114", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.26114"}} @misc{arxiv_2605_26114, title = {{MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research}}, author = {{Dingbang Wu} and {Rui Hao} and {Haiyang Wang} and {Shuzhe Wu} and {Han Xiao} and {Zhenghong Li} and {Bojiang Zhou} and {Zheng Ju} and {Zichen Liu} and {Lue Fan} and {Zhaoxiang Zhang}}, year = {2026}, eprint = {2605.26114v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.26114v3}, note = {First published: 2026-05-25; Recorded arXiv version: v3; Recorded version updated: 2026-09-23T17:59:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.26144", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2605.26144"}} @misc{arxiv_2605_26144, title = {{VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents}}, author = {{JunJia Guo} and {Yuhang Yao} and {Chang Li} and {Zimeng Pan} and {Jiawei} and {Zhou} and {Jingdi Chen}}, year = {2026}, eprint = {2605.26144v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.26144v4}, note = {First published: 2026-05-22; Recorded arXiv version: v4; Recorded version updated: 2026-09-29T00:12:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.26546", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.26546"}} @misc{arxiv_2605_26546, title = {{MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration}}, author = {{Runxi Huang} and {Liyu Zhang} and {Shengzhong Liu} and {Xiaomin Ouyang}}, year = {2026}, eprint = {2605.26546v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.26546v1}, note = {First published: 2026-05-26; Recorded arXiv version: v1; Recorded version updated: 2026-05-26T04:53:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.27761", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.27761"}} @misc{arxiv_2605_27761, title = {{AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications}}, author = {{Yifan Sui} and {Xin Huang} and {Hongbing Li} and {Fang Xu} and {Jiahe Lv} and {Haolong Yan} and {Yeqing Shen} and {Litao Liu} and {Zhimin Fan} and {Ziyang Meng} and {Jia Wang} and {Junbo Qi} and {Kaijun Tan} and {Zheng Ge} and {Xiangyu Zhang} and {Daxin Jiang} and {Osamu Yoshie}}, year = {2026}, eprint = {2605.27761v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.27761v1}, note = {First published: 2026-05-26; Recorded arXiv version: v1; Recorded version updated: 2026-05-26T23:19:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.28116", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.28116"}} @misc{arxiv_2605_28116, title = {{MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content}}, author = {{Ruoqi Guo} and {Yi Liu} and {Gelei Deng} and {Yiheng Xiong} and {Yuekang Li} and {Ying Zhang} and {Leo Yu Zhang} and {Lida Zhao} and {Ji Jie} and {Yuxiao Lu}}, year = {2026}, eprint = {2605.28116v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.28116v1}, note = {First published: 2026-05-27; Recorded arXiv version: v1; Recorded version updated: 2026-05-27T08:09:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.28258", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2605.28258"}} @misc{arxiv_2605_28258, title = {{GUI Agents for Continual Game Generation}}, author = {{Yixu Huang} and {Bo Li} and {Na Li} and {Zhe Wang} and {Kaijie Chen} and {Haonan Ge} and {Qingyi Si} and {Yuanzhe Shen} and {Ruihan Yang} and {Guangjing Wang} and {Hongcheng Guo}}, year = {2026}, eprint = {2605.28258v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.28258v2}, note = {First published: 2026-05-27; Recorded arXiv version: v2; Recorded version updated: 2026-10-02T05:26:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.28534", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.28534"}} @misc{arxiv_2605_28534, title = {{GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection}}, author = {{Zheng Wu} and {Chengcheng Han} and {Zhengxi Lu} and {Tianjie Ju} and {Yanyu Chen} and {Qi Gu} and {Xunliang Cai} and {Zhuosheng Zhang}}, year = {2026}, eprint = {2605.28534v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.28534v1}, note = {First published: 2026-05-27; Recorded arXiv version: v1; Recorded version updated: 2026-05-27T14:29:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.28646", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.28646"}} @misc{arxiv_2605_28646, title = {{MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution}}, author = {{Yanqiu Zhao} and {Dongying Zheng} and {Kaibo Huang} and {Yukun Wei} and {Zhongliang Yang} and {Linna Zhou}}, year = {2026}, eprint = {2605.28646v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.28646v2}, note = {First published: 2026-05-27; Recorded arXiv version: v2; Recorded version updated: 2026-05-29T04:03:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.29486", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.29486"}} @misc{arxiv_2605_29486, title = {{PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents}}, author = {{Yuxuan Liu} and {Xin Lai} and {Junyi Li} and {Pengyuan Lyu} and {Jason} and {Yiduo Guo} and {Zhengyao Fang} and {Yang Ding} and {Yi Zhang} and {Weinong Wang} and {Huawen Shen} and {Xingran Zhou} and {Liang Wu} and {Fei Tang} and {Sunqi Fan} and {Shangpin Peng} and {Zheng Ruan} and {Anran Zhang} and {Chengquan Zhang} and {Han Hu} and {Benyou Wang} and {Ji-Rong Wen} and {Rui Yan} and {Zhengyang Tang}}, year = {2026}, eprint = {2605.29486v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.29486v3}, note = {First published: 2026-05-28; Recorded arXiv version: v3; Recorded version updated: 2026-09-28T15:27:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2605.29534", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.29534"}} @misc{arxiv_2605_29534, title = {{UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents}}, author = {{Yuxiang Chai} and {Han Xiao} and {Xinyu Fu} and {Jinpeng Chen} and {Rui Liu} and {Hongsheng Li}}, year = {2026}, eprint = {2605.29534v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.29534v1}, note = {First published: 2026-05-28; Recorded arXiv version: v1; Recorded version updated: 2026-05-28T07:49:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.01533", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.01533"}} @misc{arxiv_2606_01533, title = {{Multi-Agent Computer Use}}, author = {{Jing Yu Koh} and {Ruslan Salakhutdinov} and {Daniel Fried}}, year = {2026}, eprint = {2606.01533v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.01533v1}, note = {First published: 2026-06-01; Recorded arXiv version: v1; Recorded version updated: 2026-06-01T01:29:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.01790", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.01790"}} @misc{arxiv_2606_01790, title = {{STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models}}, author = {{Yuhang Han} and {Wenzheng Yang} and {Yujie Chen} and {Xiangqi Jin} and {Yaojie Zhang} and {Siteng Huang} and {Linfeng Zhang}}, year = {2026}, eprint = {2606.01790v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.01790v1}, note = {First published: 2026-06-01; Recorded arXiv version: v1; Recorded version updated: 2026-06-01T07:10:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.03103", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.03103"}} @misc{arxiv_2606_03103, title = {{DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration}}, author = {{Wenkai Wang} and {Tao Xiong} and {Jingchen Ni} and {Yunpeng Bao} and {Xiyun Li} and {Tianqi Liu} and {Hongcan Guo} and {Zilong Huang} and {Shengyu Zhang}}, year = {2026}, eprint = {2606.03103v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.03103v1}, note = {First published: 2026-06-02; Recorded arXiv version: v1; Recorded version updated: 2026-06-02T03:42:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.03203", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.03203"}} @misc{arxiv_2606_03203, title = {{MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents}}, author = {{Jia Yu} and {Zilong Wang} and {Xinyang Jiang} and {Dongsheng Li} and {Shuo Wang}}, year = {2026}, eprint = {2606.03203v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.03203v1}, note = {First published: 2026-06-02; Recorded arXiv version: v1; Recorded version updated: 2026-06-02T06:02:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.03854", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2606.03854"}} @misc{arxiv_2606_03854, title = {{CLI-Anything: Towards Agent-Native Computer Use}}, author = {{Yuhao Yang} and {Tianyu Fan} and {Chao Huang}}, year = {2026}, eprint = {2606.03854v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.03854v1}, note = {First published: 2026-06-02; Recorded arXiv version: v1; Recorded version updated: 2026-06-02T16:30:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.04391", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.04391"}} @misc{arxiv_2606_04391, title = {{Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval}}, author = {{Jiaxi Li} and {Ke Deng} and {Yun Wang} and {Jingyuan Huang} and {Yucheng Shi} and {Qiaoyu Tan} and {Jin Lu} and {Ninghao Liu}}, year = {2026}, eprint = {2606.04391v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.04391v1}, note = {First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T03:11:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.04701", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.04701"}} @misc{arxiv_2606_04701, title = {{Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms}}, author = {{Jiashu Yao} and {Heyan Huang} and {Daiqing Wu} and {Wangke Chen} and {Huaxi Ai} and {Haoyu Wen} and {Zeming Liu} and {Yuhang Guo}}, year = {2026}, eprint = {2606.04701v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.04701v1}, note = {First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T10:25:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.05233", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.05233"}} @misc{arxiv_2606_05233, title = {{Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming}}, author = {{Nicholas Saban}}, year = {2026}, eprint = {2606.05233v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.05233v1}, note = {First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T01:21:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.05597", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.05597"}} @misc{arxiv_2606_05597, title = {{AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents}}, author = {{Hao Bai} and {Rui Yang} and {Chenlu Ye} and {Spencer Whitehead} and {Aviral Kumar} and {Tong Zhang}}, year = {2026}, eprint = {2606.05597v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.05597v3}, note = {First published: 2026-06-04; Recorded arXiv version: v3; Recorded version updated: 2026-08-07T17:58:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.06322", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.06322"}} @misc{arxiv_2606_06322, title = {{DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions}}, author = {{Nathan Bout} and {Maxime Langevin} and {Ronan Riochet}}, year = {2026}, eprint = {2606.06322v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.06322v1}, note = {First published: 2026-06-04; Recorded arXiv version: v1; Recorded version updated: 2026-06-04T15:57:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.06560", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.06560"}} @misc{arxiv_2606_06560, title = {{MacArena: Benchmarking Computer Use Agents on an Online macOS Environment}}, author = {{Victor Muryn} and {Maksym Shamrai} and {Sofiia Mazepa} and {Yehor Khodysko}}, year = {2026}, eprint = {2606.06560v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.06560v1}, note = {First published: 2026-06-04; Recorded arXiv version: v1; Recorded version updated: 2026-06-04T14:01:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.06708", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.06708"}} @misc{arxiv_2606_06708, title = {{Signal-Driven Observation for Long-Horizon Web Agents}}, author = {{Shubham Gaur} and {Ian Lane}}, year = {2026}, eprint = {2606.06708v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.06708v2}, note = {First published: 2026-06-04; Recorded arXiv version: v2; Recorded version updated: 2026-08-04T18:57:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.07027", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.07027"}} @misc{arxiv_2606_07027, title = {{StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents}}, author = {{Haojie Hao} and {Longkun Hao} and {Yihang Lou} and {Yan Bai} and {Zhenyang Li} and {Zhichao Yang} and {Dongshuo Huang} and {Hongyu Lin} and {Lanqing Hong} and {Jiakai Wang} and {Xianglong Liu}}, year = {2026}, eprint = {2606.07027v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.07027v2}, note = {First published: 2026-06-05; Recorded arXiv version: v2; Recorded version updated: 2026-06-12T07:28:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.07594", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.07594"}} @misc{arxiv_2606_07594, title = {{Syll: Open-Source Personal Automation with Cross-Surface Execution}}, author = {{Bo Zhang} and {Borui Zhang} and {Chenghao Jiang} and {Minglei Shi} and {Xiaofeng Wang} and {Zheng Zhu} and {Jie Zhou} and {Jiwen Lu}}, year = {2026}, eprint = {2606.07594v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.07594v1}, note = {First published: 2026-05-28; Recorded arXiv version: v1; Recorded version updated: 2026-05-28T17:59:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.09399", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.09399"}} @misc{arxiv_2606_09399, title = {{RunAgent SuperBrowser: A Theory of Autonomous Web Navigation Grounded in Human Browsing Behaviour}}, author = {{Radeen Mostafa} and {Sawradip Saha}}, year = {2026}, eprint = {2606.09399v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.09399v1}, note = {First published: 2026-06-08; Recorded arXiv version: v1; Recorded version updated: 2026-06-08T12:18:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.09426", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.09426"}} @misc{arxiv_2606_09426, title = {{WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces}}, author = {{Wanli Li} and {Bowen Zhou} and {Yunyao Yu} and {Zhou Xu} and {Yifan Yang} and {Dongsheng Li} and {Caihua Shan}}, year = {2026}, eprint = {2606.09426v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.09426v3}, note = {First published: 2026-06-08; Recorded arXiv version: v3; Recorded version updated: 2026-07-06T14:25:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.09447", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.09447"}} @misc{arxiv_2606_09447, title = {{AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement Learning}}, author = {{Bojie Rong} and {Zheyu Shen} and {Qiaoping Wang} and {Pengfei Kang} and {Yang Xu} and {Yawen Wei} and {Hanyu Wu} and {Zhi Zhao} and {Leihao Pei} and {Linquan Jiang}}, year = {2026}, eprint = {2606.09447v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.09447v1}, note = {First published: 2026-06-08; Recorded arXiv version: v1; Recorded version updated: 2026-06-08T12:55:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.09764", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.09764"}} @misc{arxiv_2606_09764, title = {{iOSWorld: A Benchmark for Personally Intelligent Phone Agents}}, author = {{Lawrence Keunho Jang} and {Mareks Woodside} and {Geronimo Carom} and {Andrew Keunwoo Jang} and {Jing Yu Koh} and {Ruslan Salakhutdinov}}, year = {2026}, eprint = {2606.09764v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.09764v1}, note = {First published: 2026-06-08; Recorded arXiv version: v1; Recorded version updated: 2026-06-08T17:27:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.10423", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.10423"}} @misc{arxiv_2606_10423, title = {{WebChallenger: A Reliable and Efficient Generalist Web Agent}}, author = {{Jayoo Hwang} and {Xiaowen Zhang} and {Vedant Padwal}}, year = {2026}, eprint = {2606.10423v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.10423v1}, note = {First published: 2026-06-09; Recorded arXiv version: v1; Recorded version updated: 2026-06-09T04:53:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.10522", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.10522"}} @misc{arxiv_2606_10522, title = {{GUI-AC: Enhancing Continual Learning in GUI Agents}}, author = {{Can Lin} and {Tao Feng} and {Hangjie Yuan} and {Dan Zhang} and {Yifan Zhu} and {Zhonghong Ou}}, year = {2026}, eprint = {2606.10522v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.10522v2}, note = {First published: 2026-06-09; Recorded arXiv version: v2; Recorded version updated: 2026-07-06T06:23:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.11042", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.11042"}} @misc{arxiv_2606_11042, title = {{Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields}}, author = {{Liya Zhu} and {Jingzhe Ding} and {Jian Zhang} and {Jianbo Xue} and {Shihao Liang} and {Ge Zhang} and {Yi Zhu} and {Duju Zeng} and {Xiang Gao} and {Qingshui Gu} and {Mailun Gao} and {Huimin Che} and {Yan Zhao} and {Peiheng Zhou} and {Haojun Wang} and {Chaobo Xian} and {Lili Le} and {Chi Wu} and {Yiwei Liu} and {Shengda Long} and {Jiale Yang} and {Fangzhi Xu} and {Sijin Wu} and {Haodong Duan} and {Chao He} and {Zhaojian Li} and {Minchao Wang} and {Huan Zhou} and {Jiani Hou} and {Chuqian Yu} and {Weiran Shi} and {Hongwan Gao} and {Jiamin Chen} and {Guanhong Chen} and {Tingqin Luo} and {Kaiyuan Zhang} and {Zhixin Yao} and {Qing Hua} and {Yuhao Jiang} and {Jin Chen} and {Pu Chen} and {Zhenyu Hu} and {Xingyu Li} and {Zhengxuan Jiang} and {Meng Cao} and {Tianfeng Long} and {Haozhe Wang} and {Mingzhang Wang} and {Yichen Zhang} and {Yiming Dai} and {Chenchen Zhang} and {Jiaying Wang} and {Xinying Liu} and {Xingzu Liu} and {Lingling Zhang} and {Xinjie Chen} and {Yujia Qin} and {Wangchunshu Zhou} and {Zhiyong Wu} and {Yang Liu} and {Jiaheng Liu} and {Lei Zhang} and {Shen Yan} and {Wenhao Huang} and {Zaiyuan Wang} and {Xiaolong Chang}}, year = {2026}, eprint = {2606.11042v4}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.11042v4}, note = {First published: 2026-06-09; Recorded arXiv version: v4; Recorded version updated: 2026-07-17T12:22:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.11078", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.11078"}} @misc{arxiv_2606_11078, title = {{A History-Aware Visually Grounded Critic for Computer Use Agents}}, author = {{Jaewoo Lee} and {Zaid Khan} and {Archiki Prasad} and {Justin Chih-Yao Chen} and {Supriyo Chakraborty} and {Kartik Balasubramaniam} and {Sambit Sahu} and {Elias Stengel-Eskin} and {Hyunji Lee} and {Mohit Bansal}}, year = {2026}, eprint = {2606.11078v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.11078v1}, note = {First published: 2026-06-09; Recorded arXiv version: v1; Recorded version updated: 2026-06-09T16:39:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.12485", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.12485"}} @misc{arxiv_2606_12485, title = {{Speculative Rollback Correction for Quality-Diverse Web Agent Imitation}}, author = {{Longkun Hao} and {Hongyu Lin} and {Hao Li} and {Zhuowen Liu} and {Zhichao Yang} and {Haojie Hao} and {Dongshuo Huang} and {Haitao Yang} and {Hongyu Ge} and {Ming jie Xie} and {Yanjun Wu} and {Zi Hao Yin} and {Yan Bai} and {Yihang Lou}}, year = {2026}, eprint = {2606.12485v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.12485v2}, note = {First published: 2026-06-10; Recorded arXiv version: v2; Recorded version updated: 2026-08-17T02:54:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.12666", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.12666"}} @misc{arxiv_2606_12666, title = {{CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents}}, author = {{Siyu Shen} and {Fenghao Xu} and {Wenrui Diao} and {Kehuan Zhang}}, year = {2026}, eprint = {2606.12666v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.12666v2}, note = {First published: 2026-06-10; Recorded arXiv version: v2; Recorded version updated: 2026-06-16T03:15:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.13239", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2606.13239"}} @misc{arxiv_2606_13239, title = {{ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm}}, author = {{Jiaxin Ai} and {Tao Hu} and {Xuemeng Yang} and {Shu Zou} and {Hairong Zhang} and {Daocheng Fu} and {Yu Yang} and {Hongbin Zhou} and {Nianchen Deng} and {Pinlong Cai} and {Zhongyuan Wang} and {Botian Shi} and {Kaipeng Zhang} and {Licheng Wen}}, year = {2026}, eprint = {2606.13239v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.13239v2}, note = {First published: 2026-06-11; Recorded arXiv version: v2; Recorded version updated: 2026-06-30T03:31:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.13385", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.13385"}} @misc{arxiv_2606_13385, title = {{Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents}}, author = {{Zihao Wang} and {Yiming Li} and {Yutong Wu} and {Kangjie Chen} and {Zheyu Liu} and {Fok Kar Wai} and {Pin-Yu Chen} and {Vrizlynn L. L. Thing} and {Bo Li} and {Dacheng Tao} and {Tianwei Zhang}}, year = {2026}, eprint = {2606.13385v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.13385v2}, note = {First published: 2026-06-11; Recorded arXiv version: v2; Recorded version updated: 2026-07-27T14:19:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.14106", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.14106"}} @misc{arxiv_2606_14106, title = {{Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents}}, author = {{Seoyoung Choi} and {Minseok Ko} and {Hyunseok Lee} and {Kunwoong Kim} and {Woomin Song} and {Chanseok Jeon} and {Jinwoo Shin}}, year = {2026}, eprint = {2606.14106v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.14106v1}, note = {First published: 2026-06-12; Recorded arXiv version: v1; Recorded version updated: 2026-06-12T04:39:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.14579", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.14579"}} @misc{arxiv_2606_14579, title = {{VISTA: View-Consistent Self-Verified Training for GUI Grounding}}, author = {{Xinyu Qiu} and {Yunzhu Zhang} and {Heng Jia} and {Shuheng Shen} and {Changhua Meng} and {Linchao Zhu}}, year = {2026}, eprint = {2606.14579v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.14579v1}, note = {First published: 2026-06-12; Recorded arXiv version: v1; Recorded version updated: 2026-06-12T15:58:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.14832", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.14832"}} @misc{arxiv_2606_14832, title = {{PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions}}, author = {{Chenxin Li} and {Zhengyao Fang} and {Zhengyang Tang} and {Pengyuan Lyu} and {Xingran Zhou} and {Xin Lai} and {Fei Tang} and {Liang Wu} and {Yiduo Guo} and {Weinong Wang} and {Junyi Li} and {Yi Zhang} and {Yang Ding} and {Huawen Shen} and {Sunqi Fan} and {Shangpin Peng} and {Zheng Ruan} and {Anran Zhang} and {Benyou Wang} and {Chengquan Zhang} and {Han Hu}}, year = {2026}, eprint = {2606.14832v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.14832v1}, note = {First published: 2026-06-12; Recorded arXiv version: v1; Recorded version updated: 2026-06-12T15:01:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.15017", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.15017"}} @misc{arxiv_2606_15017, title = {{Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents}}, author = {{Sina Hajimiri} and {Masih Aminbeidokhti} and {Jose Dolz} and {Ismail Ben Ayed} and {Issam H. Laradji} and {Spandana Gella} and {Nicolas Gontier}}, year = {2026}, eprint = {2606.15017v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.15017v2}, note = {First published: 2026-06-12; Recorded arXiv version: v2; Recorded version updated: 2026-08-30T17:49:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.15034", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.15034"}} @misc{arxiv_2606_15034, title = {{OSGuard: A Benchmark for Safety in Computer-Use Agents}}, author = {{Mina Mohammadmirzaei} and {Jeffrey Flanigan}}, year = {2026}, eprint = {2606.15034v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.15034v3}, note = {First published: 2026-06-13; Recorded arXiv version: v3; Recorded version updated: 2026-10-09T19:45:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.16659", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.16659"}} @misc{arxiv_2606_16659, title = {{FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection}}, author = {{Y. H. Zhou} and {Z. M. Ma} and {Y. J. Zhou} and {Y. T. Li} and {H. X. Xiang} and {Y. M. Cheng} and {T. L. Chen} and {K. J. Zhang} and {Z. H. Nan} and {J. H. Ni} and {Z. Wu} and {Q. Y. Pan} and {S. Zhang} and {S. Cheng} and {M. Y. Luo}}, year = {2026}, eprint = {2606.16659v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.16659v1}, note = {First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T12:53:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.16748", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.16748"}} @misc{arxiv_2606_16748, title = {{MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents}}, author = {{Lawrence Keunho Jang} and {Andrew Keunwoo Jang} and {Jing Yu Koh} and {Ruslan Salakhutdinov}}, year = {2026}, eprint = {2606.16748v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.16748v1}, note = {First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T14:08:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.16802", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.16802"}} @misc{arxiv_2606_16802, title = {{LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control}}, author = {{Anqi Zou} and {Han Deng} and {Chengyu Zhang} and {Junquan Hu} and {Yu Wang} and {Yuxiang Xing} and {Aokai Zhang} and {Hanling Zhang} and {Zhaoyang Liu} and {Ben Fei} and {Zhihui Wang} and {Wanli Ouyang}}, year = {2026}, eprint = {2606.16802v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.16802v1}, note = {First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T14:42:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.17321", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.17321"}} @misc{arxiv_2606_17321, title = {{ProCUA-SFT Technical Report}}, author = {{Jaehun Jung} and {Ximing Lu} and {Brandon Cui} and {Muhammad Khalifa} and {Shaokun Zhang} and {Hao Zhang} and {Jin Xu} and {Amala Sanjay Deshmukh} and {Karan Sapra} and {Andrew Tao} and {Yejin Choi} and {Jan Kautz} and {Mingjie Liu} and {Yi Dong}}, year = {2026}, eprint = {2606.17321v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.17321v1}, note = {First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T22:04:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.17929", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.17929"}} @misc{arxiv_2606_17929, title = {{PreAct: Computer-Using Agents that Get Faster on Repeated Tasks}}, author = {{Bojie Li}}, year = {2026}, eprint = {2606.17929v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.17929v1}, note = {First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T13:40:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.18101", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.18101"}} @misc{arxiv_2606_18101, title = {{Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding}}, author = {{Jingyuan Huang} and {Zuming Huang} and {Yucheng Shi} and {Tianze Yang} and {Xiaoming Zhai} and {Wei Chu} and {Ninghao Liu}}, year = {2026}, eprint = {2606.18101v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.18101v2}, note = {First published: 2026-06-16; Recorded arXiv version: v2; Recorded version updated: 2026-06-17T08:58:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.18448", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.18448"}} @misc{arxiv_2606_18448, title = {{VISUALSKILL: Multimodal Skills for Computer-Use Agents}}, author = {{Ziyan Jiang} and {Li An} and {Yujian Liu} and {Jiabao Ji} and {Qiucheng Wu} and {Jacob Andreas} and {Yang Zhang} and {Shiyu Chang}}, year = {2026}, eprint = {2606.18448v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.18448v1}, note = {First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T19:57:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.18671", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.18671"}} @misc{arxiv_2606_18671, title = {{HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification}}, author = {{Yujin Zhang} and {Daye Nam}}, year = {2026}, eprint = {2606.18671v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.18671v1}, note = {First published: 2026-06-17; Recorded arXiv version: v1; Recorded version updated: 2026-06-17T04:13:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.18890", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.18890"}} @misc{arxiv_2606_18890, title = {{Skill-Guided Continuation Distillation for GUI Agents}}, author = {{Zhimin Fan} and {Hongwei Yu} and {Yeqing Shen} and {Haolong Yan} and {Guozhen Peng} and {Tianhao Peng} and {Yudong Zhang} and {Xiaowen Zhang} and {Kaijun Tan} and {Zheng Ge} and {Xiangyu Zhang} and {Daxin Jiang}}, year = {2026}, eprint = {2606.18890v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.18890v1}, note = {First published: 2026-06-17; Recorded arXiv version: v1; Recorded version updated: 2026-06-17T10:07:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.19388", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2606.19388"}} @misc{arxiv_2606_19388, title = {{Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?}}, author = {{Li Gu} and {Zihuan Jiang} and {Linqiang Guo} and {Zhixiang Chi} and {Ziqiang Wang} and {Huan Liu} and {Yuanhao Yu} and {Tse-Hsun Chen} and {Yang Wang}}, year = {2026}, eprint = {2606.19388v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.19388v1}, note = {First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T02:36:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.19926", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.19926"}} @misc{arxiv_2606_19926, title = {{MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management}}, author = {{Guangyi Liu} and {Gao Wu} and {Congxiao Liu} and {Pengxiang Zhao} and {Liang Liu} and {Mading Li} and {Qi Zhang} and {Mengyan Wang} and {Liang Guo} and {Yong Liu}}, year = {2026}, eprint = {2606.19926v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.19926v1}, note = {First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T08:26:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.19930", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.19930"}} @misc{arxiv_2606_19930, title = {{MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization}}, author = {{Guangyi Liu} and {Pengxiang Zhao} and {Gao Wu} and {Yiwen Yin} and {Mading Li} and {Liang Liu} and {Congxiao Liu} and {Zhang Qi} and {Mengyan Wang} and {Liang Guo} and {Jiangning Zhang} and {Yong Liu}}, year = {2026}, eprint = {2606.19930v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.19930v2}, note = {First published: 2026-06-18; Recorded arXiv version: v2; Recorded version updated: 2026-08-07T03:54:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.20363", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.20363"}} @misc{arxiv_2606_20363, title = {{Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining}}, author = {{Yuexing Hao} and {Xiaomin Li}}, year = {2026}, eprint = {2606.20363v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.20363v1}, note = {First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T15:25:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.20622", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.20622"}} @misc{arxiv_2606_20622, title = {{Darwin Mobile Agent: A Roadmap for Self-Evolution}}, author = {{Daniel Beechey} and {Derek Yuen} and {Jianheng Liu} and {Dezhao Luo} and {Tiantian He} and {Weilin Luo} and {Jun Wang} and {Kun Shao}}, year = {2026}, eprint = {2606.20622v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.20622v1}, note = {First published: 2026-05-26; Recorded arXiv version: v1; Recorded version updated: 2026-05-26T13:32:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.20717", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.20717"}} @misc{arxiv_2606_20717, title = {{MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents}}, author = {{Xuelong Dai} and {Jianyu Ma} and {Boyang Ma} and {Biwei Yan} and {Yijun Yang} and {Yue Zhang}}, year = {2026}, eprint = {2606.20717v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.20717v2}, note = {First published: 2026-06-16; Recorded arXiv version: v2; Recorded version updated: 2026-10-15T04:29:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.20785", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.20785"}} @misc{arxiv_2606_20785, title = {{Fara-1.5: Scalable Learning Environments for Computer Use Agents}}, author = {{Ahmed Awadallah} and {Sahil Gupta} and {Yash Lara} and {Yadong Lu} and {Hussein Mozannar} and {Akshay Nambi} and {Zach Nussbaum} and {Yash Pandya} and {Aravind Rajeswaran} and {Corby Rosset} and {Alexey Taymanov} and {Luiz do Valle} and {Vibhav Vineet} and {Spencer Whitehead} and {Andrew Zhao}}, year = {2026}, eprint = {2606.20785v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.20785v2}, note = {First published: 2026-06-18; Recorded arXiv version: v2; Recorded version updated: 2026-07-22T17:47:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.20910", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.20910"}} @misc{arxiv_2606_20910, title = {{Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents}}, author = {{Dayeon Kang} and {Hyejun Jeong} and {Jade Sheffey} and {Pubali Datta} and {Amir Houmansadr}}, year = {2026}, eprint = {2606.20910v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.20910v1}, note = {First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T20:07:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.21654", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.21654"}} @misc{arxiv_2606_21654, title = {{ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks}}, author = {{Vincent Siu} and {Manasi Sharma} and {Dawn Song} and {Daniel Yue Zhang} and {Chenguang Wang} and {Ying Liu}}, year = {2026}, eprint = {2606.21654v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.21654v2}, note = {First published: 2026-06-19; Recorded arXiv version: v2; Recorded version updated: 2026-08-19T17:29:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.22557", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.22557"}} @misc{arxiv_2606_22557, title = {{MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop}}, author = {{Yikun Fu} and {Bowen Fu} and {Zhenyu Wu} and {Shuang Cheng} and {Xiaowei Sun} and {Bowen Yang} and {Zehao Li} and {Yibo Zhao} and {Zichen Ding} and {Zhoumianze Liu} and {Shijie Wang} and {Biqing Qi} and {Bowen Zhou}}, year = {2026}, eprint = {2606.22557v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.22557v1}, note = {First published: 2026-06-21; Recorded arXiv version: v1; Recorded version updated: 2026-06-21T15:32:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.22948", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.22948"}} @misc{arxiv_2606_22948, title = {{ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents}}, author = {{Yincheng Zhou} and {Athena Zhuoming Zhong} and {Shijie Zhang} and {Kevin Zhang} and {Teresa Xiaotao Shang} and {Shanghang Zhang}}, year = {2026}, eprint = {2606.22948v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.22948v1}, note = {First published: 2026-06-22; Recorded arXiv version: v1; Recorded version updated: 2026-06-22T07:28:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.23189", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.23189"}} @misc{arxiv_2606_23189, title = {{Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?}}, author = {{Anmol Goel} and {Iryna Gurevych}}, year = {2026}, eprint = {2606.23189v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.23189v2}, note = {First published: 2026-06-22; Recorded arXiv version: v2; Recorded version updated: 2026-09-10T18:49:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.24515", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.24515"}} @misc{arxiv_2606_24515, title = {{Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation}}, author = {{Marta Sumyk} and {Oleksandr Kosovan}}, year = {2026}, eprint = {2606.24515v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.24515v1}, note = {First published: 2026-06-23; Recorded arXiv version: v1; Recorded version updated: 2026-06-23T12:46:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.24525", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.24525"}} @misc{arxiv_2606_24525, title = {{VisCritic: Visual State Comparison as Process Reward for GUI Agents}}, author = {{Jiachen Qian}}, year = {2026}, eprint = {2606.24525v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.24525v1}, note = {First published: 2026-06-23; Recorded arXiv version: v1; Recorded version updated: 2026-06-23T12:57:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.24551", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.24551"}} @misc{arxiv_2606_24551, title = {{GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents}}, author = {{Xiao Zhou} and {Siyue Zhang} and {Yilun Zhao} and {Jinbiao Wei} and {Tingyu Song} and {Arman Cohan} and {Chen Zhao}}, year = {2026}, eprint = {2606.24551v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.24551v1}, note = {First published: 2026-06-22; Recorded arXiv version: v1; Recorded version updated: 2026-06-22T17:05:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.25705", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.25705"}} @misc{arxiv_2606_25705, title = {{GUI agent: Guided Exploration of User-Sensitive Screens}}, author = {{Aradhana Nayak} and {Mussadiq Nazeer} and {Wang Peng} and {Feng Liu}}, year = {2026}, eprint = {2606.25705v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.25705v1}, note = {First published: 2026-06-24; Recorded arXiv version: v1; Recorded version updated: 2026-06-24T11:18:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.25760", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.25760"}} @misc{arxiv_2606_25760, title = {{Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets}}, author = {{Divake Kumar} and {Sina Tayebati} and {Devashri Naik} and {Amanda Sofie Rios} and {Nilesh Ahuja} and {Omesh Tickoo} and {Ranganath Krishnan} and {Amit Ranjan Trivedi}}, year = {2026}, eprint = {2606.25760v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.25760v2}, note = {First published: 2026-06-24; Recorded arXiv version: v2; Recorded version updated: 2026-09-29T20:55:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.25964", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.25964"}} @misc{arxiv_2606_25964, title = {{WinDOM: Self-Family Distillation for Small-Model GUI Grounding}}, author = {{Chengheng Li-Chen} and {Zhiqian Zhou} and {Hao Chen} and {Nicolas Chauvin}}, year = {2026}, eprint = {2606.25964v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.25964v1}, note = {First published: 2026-06-24; Recorded arXiv version: v1; Recorded version updated: 2026-06-24T15:35:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.27330", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.27330"}} @misc{arxiv_2606_27330, title = {{Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning}}, author = {{Tianyi Men} and {Zhuoran Jin} and {Pengfei Cao} and {Yubo Chen} and {Kang Liu} and {Jun Zhao}}, year = {2026}, eprint = {2606.27330v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.27330v1}, note = {First published: 2026-06-25; Recorded arXiv version: v1; Recorded version updated: 2026-06-25T17:44:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.28480", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2606.28480"}} @misc{arxiv_2606_28480, title = {{TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents}}, author = {{Shoufa Chen} and {Luyuan Wang} and {Xuan Yang} and {Zhiheng Liu} and {Yuren Cong} and {Yuanfeng Ji} and {Feiyan Zhou} and {Xiaohui Zhang} and {Fanny Yang} and {Belinda Zeng}}, year = {2026}, eprint = {2606.28480v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.28480v1}, note = {First published: 2026-06-26; Recorded arXiv version: v1; Recorded version updated: 2026-06-26T17:59:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.29472", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.29472"}} @misc{arxiv_2606_29472, title = {{Agent-Computer Observation Interfaces Enable Dynamic Computer Use}}, author = {{Bojie Li} and {Noah Shi}}, year = {2026}, eprint = {2606.29472v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.29472v1}, note = {First published: 2026-06-28; Recorded arXiv version: v1; Recorded version updated: 2026-06-28T15:59:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.29537", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.29537"}} @misc{arxiv_2606_29537, title = {{OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks}}, author = {{Mengqi Yuan} and {Zilong Zhou} and {Xinzhuang Xiong} and {Weiming Wu} and {Jiayang Sun} and {Jiamin Song} and {Kaiqian Cui} and {Bowen Wang} and {Haoyuan Wu} and {Yitong Li} and {Dunjie Lu} and {Haikong Lu} and {Qi Zhen} and {Xinyuan Wang} and {Jiaqi Deng} and {Yuhao Yang} and {Cheng Chen} and {Boyuan Zheng} and {Alex Su} and {Xiao Yu} and {Hao Zou} and {Saaket Agashe} and {Xing Han Lu} and {Manpreet Kaur} and {Zhengyang Qi} and {Vincent Sunn Chen} and {Frederic Sala} and {Dayiheng Liu} and {Junyang Lin} and {Zhou Yu} and {Yu Su} and {Siva Reddy} and {Xin Eric Wang} and {Peng Qi} and {Tianbao Xie} and {Tao Yu}}, year = {2026}, eprint = {2606.29537v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.29537v2}, note = {First published: 2026-06-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-13T10:30:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.29705", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.29705"}} @misc{arxiv_2606_29705, title = {{GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots}}, author = {{Sunqi Fan} and {Lingshan Chen} and {Runqi Yin} and {Qingle Liu} and {Yongming Rao} and {Meng-Hao Guo} and {Shi-Min Hu}}, year = {2026}, eprint = {2606.29705v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.29705v1}, note = {First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T02:16:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.30084", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.30084"}} @misc{arxiv_2606_30084, title = {{One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding}}, author = {{Chen Liu} and {Ling Chen} and {Hanzhang Zhou} and {Liangyu Chen} and {Chenglin Cai} and {Xin Yu} and {Steven Hoi} and {Yue Wang}}, year = {2026}, eprint = {2606.30084v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.30084v1}, note = {First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T10:20:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.30119", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.30119"}} @misc{arxiv_2606_30119, title = {{On the Internet, Nobody Knows You're an LLM Bot: Unmasking Web Agents with Multi-Layer Fingerprinting}}, author = {{Iliana Fayolle} and {Sihem Bouhenniche} and {Samuel Pélissier} and {Pierre Laperdrix} and {Clémentine Maurice} and {Walter Rudametkin}}, year = {2026}, eprint = {2606.30119v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.30119v1}, note = {First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T10:51:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.30697", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.30697"}} @misc{arxiv_2606_30697, title = {{LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents}}, author = {{Yogeswar Reddy Thota}}, year = {2026}, eprint = {2606.30697v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.30697v1}, note = {First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T03:19:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.31270", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.31270"}} @misc{arxiv_2606_31270, title = {{Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents}}, author = {{Xueqiao Sun} and {Xiaohan Wang} and {Ludwig Schmidt} and {Serena Yeung-Levy} and {Yuhui Zhang}}, year = {2026}, eprint = {2606.31270v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.31270v1}, note = {First published: 2026-06-30; Recorded arXiv version: v1; Recorded version updated: 2026-06-30T07:44:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.31410", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.31410"}} @misc{arxiv_2606_31410, title = {{Xiaomi-GUI-0 Technical Report}}, author = {{Wanxia Cao} and {Chengzhen Duan} and {Pei Fu} and {Pengzhi Gao} and {Niu Lian} and {Fazhan Liu} and {Hui Liu} and {Heng Qu} and {Qinzhuo Wu} and {Zhehao Yu} and {Tongbo Chen} and {Shiqi Cui} and {Anan Du} and {Shukai Jia} and {Yuanfa Li} and {Wei Liu} and {Yike Liu} and {Wenchao Lu} and {Zhenbo Luo} and {Haoyuan Sun} and {Jiatong Sun} and {Cheng Tan} and {Yajie Wang} and {Changqiao Wu} and {Tao Xiong} and {Jiahui Yang} and {Yuxuan Yuan} and {Ruoceng Zhang} and {Shaojie Zhang} and {Jian Zhu} and {Jian Luan} and {Cong Zou}}, year = {2026}, eprint = {2606.31410v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.31410v2}, note = {First published: 2026-06-30; Recorded arXiv version: v2; Recorded version updated: 2026-07-01T03:59:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2606.31980", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2606.31980"}} @misc{arxiv_2606_31980, title = {{DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching}}, author = {{Meng Chen} and {Anya Ji} and {Tsung-Han Wu} and {Tobias Maringgele} and {David M. Chan} and {Alane Suhr} and {Amy Pavel}}, year = {2026}, eprint = {2606.31980v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.31980v2}, note = {First published: 2026-06-30; Recorded arXiv version: v2; Recorded version updated: 2026-09-01T04:17:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.00333", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.00333"}} @misc{arxiv_2607_00333, title = {{(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents}}, author = {{Zidong Zhang} and {Zhentao Xie} and {Wenrui Diao} and {Jianliang Wu}}, year = {2026}, eprint = {2607.00333v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.00333v2}, note = {First published: 2026-07-01; Recorded arXiv version: v2; Recorded version updated: 2026-07-14T03:01:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.04334", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.04334"}} @misc{arxiv_2607_04334, title = {{Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure}}, author = {{Guijia Zhang} and {Yuxun Chen} and {Yuheng Qi} and {Harry Yang}}, year = {2026}, eprint = {2607.04334v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.04334v2}, note = {First published: 2026-07-05; Recorded arXiv version: v2; Recorded version updated: 2026-07-18T16:56:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.04425", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.04425"}} @misc{arxiv_2607_04425, title = {{UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents}}, author = {{Niu Lian} and {Tongbo Chen} and {Zhehao Yu} and {Chengzhen Duan} and {Fazhan Liu} and {Hui Liu} and {Pei Fu} and {Jian Luan} and {Heng Qu} and {Shu-Tao Xia} and {Jinpeng Wang}}, year = {2026}, eprint = {2607.04425v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.04425v2}, note = {First published: 2026-07-05; Recorded arXiv version: v2; Recorded version updated: 2026-08-10T13:11:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.05120", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.05120"}} @misc{arxiv_2607_05120, title = {{Agent Data Injection Attacks are Realistic Threats to AI Agents}}, author = {{Woohyuk Choi} and {Juhee Kim} and {Taehyun Kang} and {Jihyeon Jeong} and {Luyi Xing} and {Byoungyoung Lee}}, year = {2026}, eprint = {2607.05120v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.05120v1}, note = {First published: 2026-07-06; Recorded arXiv version: v1; Recorded version updated: 2026-07-06T14:07:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.05277", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.05277"}} @misc{arxiv_2607_05277, title = {{Untrusted Content Masking for Web Agents with Security Guarantees}}, author = {{Kristina Nikolić} and {Egor Zverev} and {Javier Rando} and {Matthew Jagielski} and {Edoardo Debenedetti} and {Florian Tramèr}}, year = {2026}, eprint = {2607.05277v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.05277v1}, note = {First published: 2026-07-06; Recorded arXiv version: v1; Recorded version updated: 2026-07-06T16:22:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.06118", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.06118"}} @misc{arxiv_2607_06118, title = {{WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation}}, author = {{Wei Dong} and {Tianyu Fu} and {Zhe Yu} and {Hanning Wang} and {Anyang Su} and {Zhizhou Fang} and {Yuyang Chen} and {Shuo Wang} and {Minghui Wu} and {Ping Jiang} and {Zhen Lei} and {Chenxu Zhao}}, year = {2026}, eprint = {2607.06118v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.06118v1}, note = {First published: 2026-07-07; Recorded arXiv version: v1; Recorded version updated: 2026-07-07T10:27:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.09773", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.09773"}} @misc{arxiv_2607_09773, title = {{EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents}}, author = {{Mianqiu Huang} and {Taofeng Xue} and {Chong Peng} and {Jinrui Ding} and {Jie Yang} and {Sicheng Fan} and {Jiale Hong} and {Yufei Gao} and {Xiaocheng Zhang} and {Linsen Guo} and {Xin Yang} and {Dengchang Zhao} and {Yuchen Xie} and {Peng Pei} and {Xunliang Xie} and {Xipeng Qiu}}, year = {2026}, eprint = {2607.09773v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.09773v2}, note = {First published: 2026-07-07; Recorded arXiv version: v2; Recorded version updated: 2026-09-04T15:47:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.10079", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.10079"}} @misc{arxiv_2607_10079, title = {{MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation}}, author = {{Chengguang Gan} and {Hanjun Wei} and {Yunhao Liang} and {Zhixi Cai} and {Qinghao Zhang} and {Shiwen Ni}}, year = {2026}, eprint = {2607.10079v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.10079v3}, note = {First published: 2026-07-11; Recorded arXiv version: v3; Recorded version updated: 2026-07-16T03:28:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.10608", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.10608"}} @misc{arxiv_2607_10608, title = {{The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory}}, author = {{Yixiong Chen} and {Xinyi Bai} and {Alan Yuille}}, year = {2026}, eprint = {2607.10608v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.10608v1}, note = {First published: 2026-07-12; Recorded arXiv version: v1; Recorded version updated: 2026-07-12T07:05:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.11185", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.11185"}} @misc{arxiv_2607_11185, title = {{SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL}}, author = {{Bowen Lv} and {Xiao Liu} and {Yanyu Ren} and {Hanyu Lai} and {Bohao Jing} and {Hanchen Zhang} and {Yanxiao Zhao} and {Shuntian Yao} and {Jie Tang} and {Yuxiao Dong}}, year = {2026}, eprint = {2607.11185v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.11185v1}, note = {First published: 2026-07-13; Recorded arXiv version: v1; Recorded version updated: 2026-07-13T07:32:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.11388", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.11388"}} @misc{arxiv_2607_11388, title = {{StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure}}, author = {{Wenyi Wu} and {Sibo Zhu} and {Kun Zhou} and {Aayush Salvi} and {Zixuan Song} and {Biwei Huang}}, year = {2026}, eprint = {2607.11388v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.11388v1}, note = {First published: 2026-07-13; Recorded arXiv version: v1; Recorded version updated: 2026-07-13T10:48:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.12625", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.12625"}} @misc{arxiv_2607_12625, title = {{KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill}}, author = {{Yunxin Li} and {Jinchao Li} and {Shibo Su} and {Zhenran Xu} and {Chenrui Zhao} and {Tongshu Bian} and {Xiaoman Liang} and {Meishan Zhang} and {Baotian Hu} and {Min Zhang}}, year = {2026}, eprint = {2607.12625v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.12625v2}, note = {First published: 2026-07-14; Recorded arXiv version: v2; Recorded version updated: 2026-07-15T04:41:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.12640", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.12640"}} @misc{arxiv_2607_12640, title = {{A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism}}, author = {{Chengguang Gan} and {Zhixi Cai} and {Yunhao Liang} and {Hanjun Wei} and {Shiwen Ni} and {Qinghao Zhang}}, year = {2026}, eprint = {2607.12640v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.12640v1}, note = {First published: 2026-07-14; Recorded arXiv version: v1; Recorded version updated: 2026-07-14T11:17:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.14443", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.14443"}} @misc{arxiv_2607_14443, title = {{Tactile: Giving Computer-Using Agents Hands and Feet}}, author = {{Yong Liu} and {Zhenyi Zhong} and {Zhanpeng Shi}}, year = {2026}, eprint = {2607.14443v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.14443v1}, note = {First published: 2026-07-16; Recorded arXiv version: v1; Recorded version updated: 2026-07-16T00:35:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.14548", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.14548"}} @misc{arxiv_2607_14548, title = {{HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents}}, author = {{Hy Vision Team} and {Huawen Shen} and {Zhengyang Tang} and {Shangpin Peng} and {Liang Wu} and {Anran Zhang} and {Weinong Wang} and {Yiduo Guo} and {Chenxin Li} and {Zhengyao Fang} and {Yang Ding} and {Junyi Li} and {Fei Tang} and {Zheng Ruan} and {Yi Zhang} and {Xingran Zhou} and {Dingchen Yang} and {Sunqi Fan} and {Zhiyi Wan} and {Han Hu} and {Xin Lai} and {Pengyuan Lyu} and {Chengquan Zhang}}, year = {2026}, eprint = {2607.14548v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.14548v1}, note = {First published: 2026-07-16; Recorded arXiv version: v1; Recorded version updated: 2026-07-16T04:12:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.15193", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.15193"}} @misc{arxiv_2607_15193, title = {{Plover: Steering GUI Agents through Plan-Centric Interaction}}, author = {{Madhumitha Venkatesan} and {Shicheng Wen} and {Jiajing Guo} and {Jorge Piazentin Ono} and {Liu Ren} and {Dongyu Liu}}, year = {2026}, eprint = {2607.15193v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.15193v1}, note = {First published: 2026-07-16; Recorded arXiv version: v1; Recorded version updated: 2026-07-16T16:48:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.15550", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.15550"}} @misc{arxiv_2607_15550, title = {{SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction}}, author = {{Xue Yu} and {Bo Yuan} and {Kailin Zhao} and {Pengshuai Yang} and {Hong Hu} and {Junlan Feng}}, year = {2026}, eprint = {2607.15550v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.15550v3}, note = {First published: 2026-07-17; Recorded arXiv version: v3; Recorded version updated: 2026-09-02T01:49:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.17050", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.17050"}} @misc{arxiv_2607_17050, title = {{EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding}}, author = {{Yaohan Yang} and {Minglei Shi} and {Borui Zhang} and {Jie Zhou} and {Jiwen Lu}}, year = {2026}, eprint = {2607.17050v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.17050v1}, note = {First published: 2026-07-19; Recorded arXiv version: v1; Recorded version updated: 2026-07-19T03:29:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.17527", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.17527"}} @misc{arxiv_2607_17527, title = {{Sidekick: Designing Communication for Effective Multitasking with Computer Use Agents}}, author = {{Ruei-Che Chang} and {Wenqian Xu} and {Dingzeyu Li} and {Bryan Wang} and {Anhong Guo}}, year = {2026}, eprint = {2607.17527v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.17527v1}, note = {First published: 2026-07-20; Recorded arXiv version: v1; Recorded version updated: 2026-07-20T04:03:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.18046", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.18046"}} @misc{arxiv_2607_18046, title = {{SEE: Structure-aware Exploring \& Exploiting for Long-horizon GUI Agent Trajectory Synthesis}}, author = {{Zhuohang Fan} and {Beichen Zhang} and {Yuanfa Li} and {Changqiao Wu} and {Wei Liu} and {Jian Luan} and {Weigang Zhang}}, year = {2026}, eprint = {2607.18046v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.18046v2}, note = {First published: 2026-07-20; Recorded arXiv version: v2; Recorded version updated: 2026-08-18T02:32:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.18659", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.18659"}} @misc{arxiv_2607_18659, title = {{Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents}}, author = {{Behzad Ousat} and {Nikita Turkmen} and {Lalchandra Rampersaud} and {Dillan Bailey} and {Amin Kharraz}}, year = {2026}, eprint = {2607.18659v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.18659v1}, note = {First published: 2026-07-21; Recorded arXiv version: v1; Recorded version updated: 2026-07-21T03:02:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.21557", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.21557"}} @misc{arxiv_2607_21557, title = {{OpenForgeRL: Train Harness-native Agents in Any Environment}}, author = {{Xiao Yu} and {Baolin Peng} and {Ruize Xu} and {Hao Zou} and {Qianhui Wu} and {Hao Cheng} and {Wenlin Yao} and {Nikhil Singh} and {Zhou Yu} and {Jianfeng Gao}}, year = {2026}, eprint = {2607.21557v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.21557v3}, note = {First published: 2026-07-23; Recorded arXiv version: v3; Recorded version updated: 2026-08-07T17:40:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.22689", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.22689"}} @misc{arxiv_2607_22689, title = {{Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents}}, author = {{Zedong Yu} and {Qianxing Li} and {Zhi Gao} and {Liuyu Xiang} and {Chenrui Shi} and {Yang Liu} and {Huiming Wu} and {Yujie Wei} and {Yuhao Fei} and {Yubo Fu} and {Zhaofeng He}}, year = {2026}, eprint = {2607.22689v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.22689v1}, note = {First published: 2026-07-17; Recorded arXiv version: v1; Recorded version updated: 2026-07-17T12:48:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.22798", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.22798"}} @misc{arxiv_2607_22798, title = {{StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents}}, author = {{Yan Yang} and {Xiangru Jian} and {Ziyang Luo} and {Zirui Zhao} and {Yutong Dai} and {Ziji Shi} and {Hanshu Yan} and {Jun Hao Liew} and {Silvio Savarese} and {Junnan Li}}, year = {2026}, eprint = {2607.22798v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.22798v1}, note = {First published: 2026-07-24; Recorded arXiv version: v1; Recorded version updated: 2026-07-24T14:17:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.23263", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.23263"}} @misc{arxiv_2607_23263, title = {{SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents}}, author = {{Yang Wan} and {Zhenhao Zhang} and {Jierui Wang} and {Xiangxin Zhou} and {Linchao Zhu}}, year = {2026}, eprint = {2607.23263v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.23263v2}, note = {First published: 2026-07-25; Recorded arXiv version: v2; Recorded version updated: 2026-09-26T12:15:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.24112", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.24112"}} @misc{arxiv_2607_24112, title = {{Scaling GUI Agents with Visual State Transitions}}, author = {{Xiangyan Liu} and {Kaixin Li} and {Haonan Wang} and {Biao Wu} and {Meng Fang} and {Longxu Dou} and {Chao Du} and {Michael Qizhe Shieh} and {Tianyu Pang}}, year = {2026}, eprint = {2607.24112v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.24112v1}, note = {First published: 2026-07-27; Recorded arXiv version: v1; Recorded version updated: 2026-07-27T07:54:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.24167", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.24167"}} @misc{arxiv_2607_24167, title = {{Falsifiable Commitment Planning for Self-Correcting Web Agents}}, author = {{Guangyi Liu} and {Huan Zhao} and {Quanming Yao}}, year = {2026}, eprint = {2607.24167v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.24167v1}, note = {First published: 2026-07-27; Recorded arXiv version: v1; Recorded version updated: 2026-07-27T08:48:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.25904", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.25904"}} @misc{arxiv_2607_25904, title = {{Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification}}, author = {{Chenrui Shi} and {Yuwei Wu} and {Yang Liu} and {Ruining Feng} and {Zirui Shang} and {Zhi Gao} and {Lifeng Fan} and {Che Sun}}, year = {2026}, eprint = {2607.25904v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.25904v2}, note = {First published: 2026-07-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-29T05:13:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.26041", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.26041"}} @misc{arxiv_2607_26041, title = {{Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?}}, author = {{Abhishek Pillai} and {Samir Kumar Nayak} and {Yuan Chen}}, year = {2026}, eprint = {2607.26041v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.26041v2}, note = {First published: 2026-07-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-29T19:07:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.28074", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28074"}} @misc{arxiv_2607_28074, title = {{Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale}}, author = {{Yash Pandya} and {Sahil Gupta} and {Sarthak Harne} and {Archana Yadav} and {Kavyansh Chourasia} and {Hussein Mozannar} and {Vibhav Vineet} and {Sara Abdali} and {Corby Rosset} and {Yash Lara} and {Ahmed Awadallah} and {Ece Kamar} and {Akshay Nambi}}, year = {2026}, eprint = {2607.28074v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28074v1}, note = {First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T11:48:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.28227", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28227"}} @misc{arxiv_2607_28227, title = {{Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents}}, author = {{Hanzhang Zhou} and {Panrong Tong} and {Xu Zhang} and {Quyu Kong} and {Chenglin Cai} and {Tianyu Xia} and {Gongjie Zhang} and {Jianan Zhang} and {Long Li} and {Long Chen} and {Lei Wang} and {Gaole Dai} and {Pengxiang Li} and {Liangyu Chen} and {Yue Wang} and {Steven Hoi}}, year = {2026}, eprint = {2607.28227v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28227v1}, note = {First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T13:58:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.28367", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28367"}} @misc{arxiv_2607_28367, title = {{How Benchmarks Mis-Score Computer-Use Agents}}, author = {{Zihan Dong} and {Zhiyuan Ma} and {Zekun Wang} and {Yunqing Li} and {Zirou Liu} and {Ruixuan Deng} and {Qishi Zhan} and {Rui Qian}}, year = {2026}, eprint = {2607.28367v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28367v1}, note = {First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T15:29:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.28399", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28399"}} @misc{arxiv_2607_28399, title = {{Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees}}, author = {{Zihan Dong} and {Rui Qian} and {Qishi Zhan} and {Dongshen Peng} and {Kaixin Li} and {Yu Li}}, year = {2026}, eprint = {2607.28399v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28399v1}, note = {First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T15:50:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.28573", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28573"}} @misc{arxiv_2607_28573, title = {{Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs}}, author = {{Woongkyu Lee} and {Jungwook Choi}}, year = {2026}, eprint = {2607.28573v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28573v1}, note = {First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T17:36:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.28609", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28609"}} @misc{arxiv_2607_28609, title = {{OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models}}, author = {{Qiushi Sun} and {Kanzhi Cheng} and {Yian Wang} and {Bowen Yang} and {Hang Yan} and {Liheng Chen} and {Fangzhi Xu} and {Zichen Ding} and {Nuo Chen} and {Jialin Cao} and {Xingdong Gong} and {Zehao Li} and {Kaiming Jin} and {Xinfeng Yuan} and {Zhoumianze Liu} and {Jingyang Gong} and {Zhangyue Yin} and {Jiahui Gao} and {Zhiyong Wu} and {Tianbao Xie} and {Jianbing Zhang} and {Ben Kao} and {Lingpeng Kong}}, year = {2026}, eprint = {2607.28609v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28609v2}, note = {First published: 2026-07-30; Recorded arXiv version: v2; Recorded version updated: 2026-08-06T17:55:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2607.29320", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.29320"}} @misc{arxiv_2607_29320, title = {{MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation}}, author = {{Hang Yan} and {Zhangxuan GU} and {Beitong Zhou} and {Jiaxuan Chen} and {Runze Li} and {Yusong Hu} and {Shuheng Shen} and {Changhua Meng}}, year = {2026}, eprint = {2607.29320v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.29320v1}, note = {First published: 2026-07-31; Recorded arXiv version: v1; Recorded version updated: 2026-07-31T11:51:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.00202", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.00202"}} @misc{arxiv_2608_00202, title = {{From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems}}, author = {{Yashaswi Malla} and {Sandra Siby}}, year = {2026}, eprint = {2608.00202v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.00202v1}, note = {First published: 2026-07-31; Recorded arXiv version: v1; Recorded version updated: 2026-07-31T18:27:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.02352", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.02352"}} @misc{arxiv_2608_02352, title = {{Qwen-CUA: Native Computer Use for (almost) Everything}}, author = {{Dunjie Lu} and {Shuai Bai} and {Tianyi Bai} and {Sicheng Fan} and {Chang Gao} and {Jian Guan} and {Feng Hu} and {Mianqiu Huang} and {Xingyang Huang} and {Yizhen Jiang} and {Yuheng Jing} and {Dehui Kong} and {Ning Li} and {Dayiheng Liu} and {Shixuan Liu} and {Zheng Liu} and {Que Shen} and {Bowen Wang} and {Junli Wang} and {Chencan Wu} and {Rui Xie} and {Tianbao Xie} and {Zhihui Xie} and {Haiyang Xu} and {An Yang} and {Tao Yu} and {Wenzhen Yuan} and {Xi Zhang} and {Zhenru Zhang} and {Mingkang Zhu} and {Zhaoqing Zhu} and {Yizhong Cao} and {Kai Dang} and {Binyuan Hui} and {Kaixin Li} and {Junyang Lin} and {Haiquan Wang} and {Zekun Wang} and {Yiheng Xu} and {Fan Yan} and {Mengqi Yuan} and {Danyang Zhang} and {Jiajun Zhang} and {Zhipeng Zhang} and {Fan Zhou} and {Fan Zhou}}, year = {2026}, eprint = {2608.02352v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.02352v1}, note = {First published: 2026-08-03; Recorded arXiv version: v1; Recorded version updated: 2026-08-03T15:04:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.02643", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.02643"}} @misc{arxiv_2608_02643, title = {{CUADebug: Diagnosing and Repairing Computer-Use Agent Failures}}, author = {{Weijia Zhang} and {Kunlun Zhu} and {Zeyi Liu} and {Yinting Chen} and {Tianyi Ma} and {Jiateng Liu} and {Jiaxun Zhang} and {Bingxuan Li} and {Xiangru Tang} and {Heng Ji} and {Jiaxuan You}}, year = {2026}, eprint = {2608.02643v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.02643v2}, note = {First published: 2026-07-31; Recorded arXiv version: v2; Recorded version updated: 2026-09-06T04:43:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.03270", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.03270"}} @misc{arxiv_2608_03270, title = {{GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs}}, author = {{Zichuan Fu} and {Shirong Wang} and {Wenlin Zhang} and {Guojing Li} and {Yimin Deng} and {Jingtong Gao} and {Junjia Qi} and {Hanyu Yan} and {Yefeng Zheng} and {Xiaopeng Li} and {Wanyu Wang} and {Xian Wu} and {Xiangyu Zhao}}, year = {2026}, eprint = {2608.03270v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.03270v1}, note = {First published: 2026-08-04; Recorded arXiv version: v1; Recorded version updated: 2026-08-04T07:47:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.03327", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.03327"}} @misc{arxiv_2608_03327, title = {{Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents}}, author = {{Siqi Fan} and {Minghao Li} and {Xiaoqian Ma} and {Wenhui Tan} and {Xiusheng Huang} and {Juntong Wu} and {Liujie Zhang} and {Shuo Shang} and {Weihang Chen}}, year = {2026}, eprint = {2608.03327v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.03327v2}, note = {First published: 2026-08-04; Recorded arXiv version: v2; Recorded version updated: 2026-08-06T07:26:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.03740", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.03740"}} @misc{arxiv_2608_03740, title = {{MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models}}, author = {{Yu Ran} and {Wentao Zhao}}, year = {2026}, eprint = {2608.03740v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.03740v2}, note = {First published: 2026-08-04; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T13:07:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.04741", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.04741"}} @misc{arxiv_2608_04741, title = {{LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents}}, author = {{Longtao Guo} and {Zelin Zhang} and {Kaifeng Huang} and {Yang Shi}}, year = {2026}, eprint = {2608.04741v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.04741v1}, note = {First published: 2026-08-05; Recorded arXiv version: v1; Recorded version updated: 2026-08-05T12:08:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.04755", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.04755"}} @misc{arxiv_2608_04755, title = {{"Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents}}, author = {{Dongsheng Chen} and {Yuxuan Li} and {Guanhua Chen} and {Jiaxin Zhang} and {Xiangyu Zhao} and {Lei Ma} and {Xin Yao} and {Xuetao Wei}}, year = {2026}, eprint = {2608.04755v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.04755v1}, note = {First published: 2026-08-05; Recorded arXiv version: v1; Recorded version updated: 2026-08-05T12:23:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.05587", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.05587"}} @misc{arxiv_2608_05587, title = {{StepReflect: Structured UI Transition Reflection for Mobile GUI Agents}}, author = {{Linqiang Guo} and {Wei Liu} and {Li Gu} and {Yang Wang} and {Tse-Hsun} and {Chen}}, year = {2026}, eprint = {2608.05587v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.05587v1}, note = {First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T04:17:27Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.05891", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.05891"}} @misc{arxiv_2608_05891, title = {{AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents}}, author = {{Weikai Xu} and {Yunren Feng} and {Haoxiang Lei} and {Kun Huang} and {Yuxuan Liu} and {Kang Zhao} and {Xiaolin Hu} and {Shuo Shang} and {Bo An}}, year = {2026}, eprint = {2608.05891v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.05891v1}, note = {First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T11:15:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.06065", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.06065"}} @misc{arxiv_2608_06065, title = {{The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents}}, author = {{Weiwei Li} and {Junzhuo Liu} and {Tong Chu} and {Hengfu Yu} and {Wen Li}}, year = {2026}, eprint = {2608.06065v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.06065v1}, note = {First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T14:10:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.06171", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.06171"}} @misc{arxiv_2608_06171, title = {{Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents}}, author = {{Jiaming Wei} and {Zekun Wu} and {Adriano Koshiyama} and {Maria Perez-Ortiz}}, year = {2026}, eprint = {2608.06171v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.06171v1}, note = {First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T15:37:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.07775", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.07775"}} @misc{arxiv_2608_07775, title = {{AndroidReality: How Far Are Mobile Agents from the Real World?}}, author = {{Xiaoou Liu} and {Longchao Da} and {Hanyang Chen} and {Yuan Ling} and {Hua Wei}}, year = {2026}, eprint = {2608.07775v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.07775v1}, note = {First published: 2026-08-07; Recorded arXiv version: v1; Recorded version updated: 2026-08-07T21:47:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.08392", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.08392"}} @misc{arxiv_2608_08392, title = {{CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception}}, author = {{Zejun Xu} and {Taiyi Chen} and {Jin Li} and {Yongtong Gu} and {Qi Cheng} and {Aixuan Lv} and {Shuai Zhu} and {Pengfei Zhu} and {Kaichen Yang} and {Boyu Sun} and {Yixian Yang} and {Mulong Xie} and {Xin Liu} and {Dagang Li} and {Xiaoteng Ma} and {Hongru Wang}}, year = {2026}, eprint = {2608.08392v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.08392v1}, note = {First published: 2026-08-09; Recorded arXiv version: v1; Recorded version updated: 2026-08-09T01:08:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.08939", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.08939"}} @misc{arxiv_2608_08939, title = {{Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection}}, author = {{Rahul Deivasigamani} and {Sayeda Faatin Alvi} and {Derqui Andrea} and {Kaushal Punjabi} and {Stjepan Picek}}, year = {2026}, eprint = {2608.08939v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.08939v1}, note = {First published: 2026-08-09; Recorded arXiv version: v1; Recorded version updated: 2026-08-09T22:13:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.09654", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.09654"}} @misc{arxiv_2608_09654, title = {{Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching}}, author = {{Yuke Li} and {Xuehan Hou}}, year = {2026}, eprint = {2608.09654v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.09654v1}, note = {First published: 2026-08-10; Recorded arXiv version: v1; Recorded version updated: 2026-08-10T14:29:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.09723", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.09723"}} @misc{arxiv_2608_09723, title = {{LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection}}, author = {{Renshan Zhang} and {Haoyang Meng} and {Yixiao He} and {Rui Shao} and {April Hua Liu} and {Liqiang Nie}}, year = {2026}, eprint = {2608.09723v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.09723v1}, note = {First published: 2026-08-10; Recorded arXiv version: v1; Recorded version updated: 2026-08-10T15:23:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.09944", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.09944"}} @misc{arxiv_2608_09944, title = {{Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents}}, author = {{Santosh Patapati}}, year = {2026}, eprint = {2608.09944v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.09944v1}, note = {First published: 2026-07-01; Recorded arXiv version: v1; Recorded version updated: 2026-07-01T16:24:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.10366", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.10366"}} @misc{arxiv_2608_10366, title = {{DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?}}, author = {{Mizanur Rahman} and {Mohammed Saidul Islam} and {Ridwan Mahbub} and {Md Tahmid Rahman Laskar} and {Shafiq Joty} and {Enamul Hoque Prince}}, year = {2026}, eprint = {2608.10366v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.10366v1}, note = {First published: 2026-08-11; Recorded arXiv version: v1; Recorded version updated: 2026-08-11T01:45:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.11434", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.11434"}} @misc{arxiv_2608_11434, title = {{Benchmarking LLM Judges for Mobile Agent Evaluation}}, author = {{Ziqiang Wang} and {Li Gu} and {Zhixiang Chi} and {Zhi Liu} and {Seyed Mehdi Ayyoubzadeh} and {Yuanhao Yu} and {Yang Wang}}, year = {2026}, eprint = {2608.11434v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.11434v1}, note = {First published: 2026-08-11; Recorded arXiv version: v1; Recorded version updated: 2026-08-11T21:00:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.12429", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.12429"}} @misc{arxiv_2608_12429, title = {{SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents}}, author = {{Ruitao Wang} and {Yuwen Hao} and {Menglin Yang}}, year = {2026}, eprint = {2608.12429v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.12429v1}, note = {First published: 2026-08-12; Recorded arXiv version: v1; Recorded version updated: 2026-08-12T12:03:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.14131", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.14131"}} @misc{arxiv_2608_14131, title = {{LegacyWorld: Atomicity-Aware Evaluation of GUI Agents for Legacy Workflows}}, author = {{Thilo Reintjes} and {Sivajeet Chand} and {Derui Zhu} and {Sushant Kumar Pandey} and {Alexander Pretschner}}, year = {2026}, eprint = {2608.14131v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.14131v1}, note = {First published: 2026-08-14; Recorded arXiv version: v1; Recorded version updated: 2026-08-14T09:36:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.14132", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.14132"}} @misc{arxiv_2608_14132, title = {{Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions}}, author = {{Xiaokai Yan} and {Jingtao Ding} and {Yong Li} and {Zhiwen Yu}}, year = {2026}, eprint = {2608.14132v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.14132v1}, note = {First published: 2026-08-14; Recorded arXiv version: v1; Recorded version updated: 2026-08-14T09:36:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.15930", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.15930"}} @misc{arxiv_2608_15930, title = {{UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations}}, author = {{Zihan Ding} and {Longxu Dou} and {Qi Gao} and {Xiangwu Guo} and {Shengchao Hu} and {Zilong Huang} and {Zihang Jiang} and {Lei Ke} and {Mengcheng Lan} and {Weixian Lei} and {Hanxuan Li} and {Honglin Li} and {Xiyun Li} and {Zaitang Li} and {Leowei Liang} and {Xin Luo} and {Haozhe Ma} and {Jiayi Mao} and {Zhoujie Pan} and {Can Qin} and {Tianyuan Qu} and {Weiqi Wang} and {Wenkai Wang} and {Yonglin Wang} and {Yuxin Wang} and {Chenxu Wu} and {Yingchen Yu} and {Chenyu Zhang} and {Yuhao Zheng}}, year = {2026}, eprint = {2608.15930v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.15930v1}, note = {First published: 2026-08-16; Recorded arXiv version: v1; Recorded version updated: 2026-08-16T20:59:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.17319", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.17319"}} @misc{arxiv_2608_17319, title = {{Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents}}, author = {{AIMAE Team} and {Tianxiang Chen} and {Yan Cheng} and {Zhangye Han} and {Xiaowei Li} and {Chang Liu} and {Cheng Liu} and {Zhongqiang Ma} and {Long Peng} and {Xiaobing Tu} and {Yinggui Wang} and {Hongliang Wei} and {Chen Wu} and {Daiping Xin} and {Kunyu Zhou} and {Pengyang Zhou} and {Peiyuan Chen} and {Ziyuan Chen} and {Yutao Deng} and {Chunyu Dong} and {Xiangyu Fu} and {Yicheng Feng} and {Ruian He} and {Haochen Li} and {Miancan Liu} and {Zhengqin Liu} and {Wei Peng} and {Jinkui Ren} and {Haoyu Tan} and {Dong Xiao} and {Rongkun Xue} and {Shujian Yang} and {Xianhang Ye} and {Ziqi Yuan} and {Ziyang Yu} and {Linghan Zhang} and {Xiantao Zhang} and {Xuanpu Zhao} and {Yinan Zhao} and {Zhenghui Zhao} and {Bin Zhu} and {Likai Zou}}, year = {2026}, eprint = {2608.17319v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.17319v1}, note = {First published: 2026-08-18; Recorded arXiv version: v1; Recorded version updated: 2026-08-18T03:23:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.17659", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.17659"}} @misc{arxiv_2608_17659, title = {{MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps}}, author = {{Sujin Chen} and {Lijun Li} and {Tianyi Du} and {Jing Shao}}, year = {2026}, eprint = {2608.17659v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.17659v1}, note = {First published: 2026-08-18; Recorded arXiv version: v1; Recorded version updated: 2026-08-18T11:33:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.18307", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.18307"}} @misc{arxiv_2608_18307, title = {{ComponentBench: Diagnosing Component-Level Failures in Computer-Use Agents}}, author = {{Tianchen Guan} and {Xinlei Lin} and {Royce Cheng-Yue} and {Xiangjun Wang} and {Shuyan Zhou}}, year = {2026}, eprint = {2608.18307v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.18307v1}, note = {First published: 2026-08-18; Recorded arXiv version: v1; Recorded version updated: 2026-08-18T20:38:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.20319", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.20319"}} @misc{arxiv_2608_20319, title = {{Inducing Task Models from Computer-Use Traces}}, author = {{Yucheng Jiang} and {Zora Zhiruo Wang} and {Ruishi Chen} and {Diyi Yang}}, year = {2026}, eprint = {2608.20319v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.20319v1}, note = {First published: 2026-08-20; Recorded arXiv version: v1; Recorded version updated: 2026-08-20T17:57:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.21794", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.21794"}} @misc{arxiv_2608_21794, title = {{Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web}}, author = {{Qijia Chen} and {Giulio Jacucci}}, year = {2026}, eprint = {2608.21794v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.21794v1}, note = {First published: 2026-08-22; Recorded arXiv version: v1; Recorded version updated: 2026-08-22T06:30:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.21830", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.21830"}} @misc{arxiv_2608_21830, title = {{Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents}}, author = {{Chengyang Gu} and {Le Zhang} and {Jingbo Zhou} and {Yize Chen} and {Yu Shi} and {Siqi Bao} and {Zheng-Fan Wu} and {Hua Wu} and {Hui Xiong}}, year = {2026}, eprint = {2608.21830v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.21830v1}, note = {First published: 2026-08-22; Recorded arXiv version: v1; Recorded version updated: 2026-08-22T08:01:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.21832", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.21832"}} @misc{arxiv_2608_21832, title = {{GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding}}, author = {{Md Abrar Jahin} and {Md Rizwan Parvez}}, year = {2026}, eprint = {2608.21832v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.21832v2}, note = {First published: 2026-08-22; Recorded arXiv version: v2; Recorded version updated: 2026-08-27T07:03:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.21898", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.21898"}} @misc{arxiv_2608_21898, title = {{Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning}}, author = {{Chenghao Zhang} and {Yuxi Cheng} and {Saisai Hu} and {Canran Xiao} and {Yikai Mao} and {Dan Roth}}, year = {2026}, eprint = {2608.21898v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.21898v2}, note = {First published: 2026-08-22; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T15:54:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.22577", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.22577"}} @misc{arxiv_2608_22577, title = {{CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents}}, author = {{Jiaxuan Luo} and {Zhanfeng Liao} and {Jiayao Teng} and {Yuan Wang}}, year = {2026}, eprint = {2608.22577v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.22577v2}, note = {First published: 2026-08-23; Recorded arXiv version: v2; Recorded version updated: 2026-08-25T04:24:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.22847", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.22847"}} @misc{arxiv_2608_22847, title = {{GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis}}, author = {{Long Zhang} and {Yuhan Chen} and {Chaoran Zhang} and {Wanxia Cao} and {Kun Huang} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Chenliang Li} and {Lixin Zou}}, year = {2026}, eprint = {2608.22847v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.22847v1}, note = {First published: 2026-08-24; Recorded arXiv version: v1; Recorded version updated: 2026-08-24T06:27:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.24015", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.24015"}} @misc{arxiv_2608_24015, title = {{Reflection with Action-Induced Visual Differences for Desktop GUI Agents}}, author = {{Yijie Ma} and {Chaoyue Niu} and {Fan Wu} and {Guihai Chen}}, year = {2026}, eprint = {2608.24015v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.24015v1}, note = {First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T03:10:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.24017", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2608.24017"}} @misc{arxiv_2608_24017, title = {{WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents}}, author = {{Lin-Fa Lee} and {YI-YU Chang} and {Kuo-Hui Yeh}}, year = {2026}, eprint = {2608.24017v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.24017v1}, note = {First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T03:16:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.24099", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.24099"}} @misc{arxiv_2608_24099, title = {{Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments}}, author = {{Guo Gan} and {Yilun Zhao} and {Cong Chen} and {Jinbiao Wei} and {Tingyu Song} and {Zheyuan Yang} and {Lin Fu} and {Hong Zhou}}, year = {2026}, eprint = {2608.24099v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.24099v1}, note = {First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T05:57:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.24174", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.24174"}} @misc{arxiv_2608_24174, title = {{Task-Adaptive Rubrics for GUI Reward Modeling}}, author = {{Tao Xiong} and {Xavier Hu} and {Wenkai Wang} and {Qinzhuo Wu} and {Changqiao Wu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Shengyu Zhang}}, year = {2026}, eprint = {2608.24174v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.24174v1}, note = {First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T07:40:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.24848", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.24848"}} @misc{arxiv_2608_24848, title = {{BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes}}, author = {{Fei Tang} and {Huawen Shen} and {Zhiqiong Lu} and {Zhengxi Lu} and {Pengyuan Lyu} and {Chengquan Zhang} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang} and {Yongliang Shen}}, year = {2026}, eprint = {2608.24848v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.24848v1}, note = {First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T17:35:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.24913", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.24913"}} @misc{arxiv_2608_24913, title = {{From Blind Edits to Verified Repair: Building Trustworthy User-Side LLM Agents for Web Accessibility}}, author = {{Lily Bundgaard Wanscher} and {Markus Heidemann Lorensen} and {Mohammed Ammad Shafiq} and {Mahyar Tourchi Moghaddam} and {Mina Alipour}}, year = {2026}, eprint = {2608.24913v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.24913v1}, note = {First published: 2026-07-26; Recorded arXiv version: v1; Recorded version updated: 2026-07-26T17:21:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.25777", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.25777"}} @misc{arxiv_2608_25777, title = {{LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents}}, author = {{Weiming Li} and {Helen Paik} and {Yulei Sui}}, year = {2026}, eprint = {2608.25777v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.25777v2}, note = {First published: 2026-08-26; Recorded arXiv version: v2; Recorded version updated: 2026-09-25T23:54:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.26204", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.26204"}} @misc{arxiv_2608_26204, title = {{ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices}}, author = {{Joy Chen} and {Alejandro Castillejo Munoz} and {Pierluca D'Oro} and {Yuxuan Sun} and {Chloe Evans} and {Joseph Tighe}}, year = {2026}, eprint = {2608.26204v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.26204v2}, note = {First published: 2026-08-25; Recorded arXiv version: v2; Recorded version updated: 2026-09-15T04:43:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.26991", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.26991"}} @misc{arxiv_2608_26991, title = {{ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions}}, author = {{Rui Xie} and {Lu Chen}}, year = {2026}, eprint = {2608.26991v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.26991v1}, note = {First published: 2026-08-27; Recorded arXiv version: v1; Recorded version updated: 2026-08-27T11:38:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.27508", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.27508"}} @misc{arxiv_2608_27508, title = {{WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement Learning}}, author = {{Yu Han} and {Tianwen Qian}}, year = {2026}, eprint = {2608.27508v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.27508v1}, note = {First published: 2026-08-27; Recorded arXiv version: v1; Recorded version updated: 2026-08-27T07:09:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.27808", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.27808"}} @misc{arxiv_2608_27808, title = {{CURA: Certified Runtime Alarms for Computer-Use Agents}}, author = {{Divake Kumar} and {Sina Tayebati} and {Devashri Naik} and {Amanda Sofie Rios} and {Nilesh Ahuja} and {Omesh Tickoo} and {Ranganath Krishnan} and {Amit Ranjan Trivedi}}, year = {2026}, eprint = {2608.27808v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.27808v1}, note = {First published: 2026-08-28; Recorded arXiv version: v1; Recorded version updated: 2026-08-28T00:50:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.27866", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.27866"}} @misc{arxiv_2608_27866, title = {{Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents}}, author = {{Jiahe Ying} and {Wendong Bu} and {Kaihang Pan} and {Bingchen Miao} and {Siyu Chen} and {Wen Wang} and {Xueming Jiang} and {Juncheng Li} and {Siliang Tang}}, year = {2026}, eprint = {2608.27866v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.27866v1}, note = {First published: 2026-08-28; Recorded arXiv version: v1; Recorded version updated: 2026-08-28T03:15:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.29305", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.29305"}} @misc{arxiv_2608_29305, title = {{Learning Simple Test-Time Environments for LLM Web Agents}}, author = {{Junxuan Li} and {Zijun Liu} and {Ziyi Huang} and {Peng Li} and {Yuzhou Liu} and {Ming Yan} and {Yang Liu}}, year = {2026}, eprint = {2608.29305v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.29305v1}, note = {First published: 2026-08-29; Recorded arXiv version: v1; Recorded version updated: 2026-08-29T14:45:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.29596", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2608.29596"}} @misc{arxiv_2608_29596, title = {{A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and Security}}, author = {{Sanket Badhe} and {Deep Shah} and {Priyanka Tiwari} and {Nehal Kathrotia}}, year = {2026}, eprint = {2608.29596v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.29596v2}, note = {First published: 2026-08-30; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T17:25:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.30038", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.30038"}} @misc{arxiv_2608_30038, title = {{ActReal: System-Level Mobile Agents Challenge Mobile Automation Detection}}, author = {{Mingshuo Wang} and {Hanqing Guo} and {Huining Li} and {Yuliang Fu} and {Jing Xu} and {Chenhan Xu}}, year = {2026}, eprint = {2608.30038v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.30038v1}, note = {First published: 2026-08-30; Recorded arXiv version: v1; Recorded version updated: 2026-08-30T20:55:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2608.30207", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.30207"}} @misc{arxiv_2608_30207, title = {{SIR: Self-improving Red-teaming for Compute Use Agents}}, author = {{Chen Xiong} and {Zhiyuan He} and {Pin-Yu Chen} and {Stjepan Picek} and {Tsung-Yi Ho}}, year = {2026}, eprint = {2608.30207v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.30207v2}, note = {First published: 2026-08-31; Recorded arXiv version: v2; Recorded version updated: 2026-10-03T10:41:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.00028", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.00028"}} @misc{arxiv_2609_00028, title = {{UI-Venus-2 Technical Report}}, author = {{Venus Team} and {Zhuohan Cai} and {Haoxing Chen} and {Jiaxuan Chen} and {Weizhi Chen} and {Changlong Gao} and {Zhangxuan Gu} and {Yuan Guo} and {Yusong Hu} and {Jianrong Jiang} and {Jianguo Li} and {Runze Li} and {Jinzhen Lin} and {Zhenyu Ma} and {Changhua Meng} and {Han Peng} and {Xinyu Qiu} and {Shuheng Shen} and {Zhongyi Shui} and {Weiqiang Wang} and {Ming Wen} and {Zhuoer Xu} and {Hang Yan} and {Kaiwen Yang} and {Ruilin Yao} and {Nanjun Yu} and {Zhengwen Zeng} and {Lianrui Zhang} and {Yunzhu Zhang} and {Zhe Zhao} and {Beitong Zhou}}, year = {2026}, eprint = {2609.00028v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.00028v1}, note = {First published: 2026-08-27; Recorded arXiv version: v1; Recorded version updated: 2026-08-27T17:15:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.00048", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.00048"}} @misc{arxiv_2609_00048, title = {{GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments}}, author = {{Lin Fu} and {Zheyuan Yang} and {Tianhui Zhang} and {Jinbiao Wei} and {Guo Gan} and {Boxu Liu} and {Yilun Zhao} and {Yu Rong}}, year = {2026}, eprint = {2609.00048v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.00048v1}, note = {First published: 2026-08-30; Recorded arXiv version: v1; Recorded version updated: 2026-08-30T05:19:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.00524", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.00524"}} @misc{arxiv_2609_00524, title = {{Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop Applications}}, author = {{Satwik Ram Kodandaram} and {Monalika Padma Reddy} and {Xiaojun Bi} and {Jiawei Zhou} and {I. V. Ramakrishnan} and {Vikas Ashok}}, year = {2026}, eprint = {2609.00524v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.00524v1}, note = {First published: 2026-09-01; Recorded arXiv version: v1; Recorded version updated: 2026-09-01T00:44:19Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.02057", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02057"}} @misc{arxiv_2609_02057, title = {{Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision}}, author = {{Sitong Pan} and {Yipeng Shen} and {Yilin Lu} and {Caiwen Ding} and {Lu Cheng} and {Qianwen Wang}}, year = {2026}, eprint = {2609.02057v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.02057v1}, note = {First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T03:34:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.02149", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02149"}} @misc{arxiv_2609_02149, title = {{OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations}}, author = {{Yixiong Xiao} and {Lang An} and {Hucheng Yang} and {Pinxue Ma} and {Yongquan Chen} and {Jingjia Cao} and {Yusai Zhao} and {Ting Wang} and {Ting Liu} and {Siqi Bao} and {Jingbo Zhou} and {Hua Wu}}, year = {2026}, eprint = {2609.02149v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.02149v3}, note = {First published: 2026-09-02; Recorded arXiv version: v3; Recorded version updated: 2026-09-10T15:52:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.02154", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02154"}} @misc{arxiv_2609_02154, title = {{WiP: Characterizing and Defending Against Mobile-Agent-Driven MFA Automation}}, author = {{Yimeng Liu} and {Hua Huang}}, year = {2026}, eprint = {2609.02154v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.02154v1}, note = {First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T06:06:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.02309", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02309"}} @misc{arxiv_2609_02309, title = {{Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization}}, author = {{Bizhe Bai} and {Jiakang Yuan} and {Hongming Wu} and {Xinyue Wang} and {Jie Ren} and {Siyao Chen} and {Yuchen Ya} and {Fan Bai} and {Pai Peng} and {Huafeng Qin} and {Tao Chen}}, year = {2026}, eprint = {2609.02309v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.02309v1}, note = {First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T08:54:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.02885", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02885"}} @misc{arxiv_2609_02885, title = {{Discriminative World Models for Web Agents}}, author = {{Kelvin Li} and {Dhruv Pendharkar} and {Anish Pahilajani} and {Chuyi Shang} and {Leon Oks} and {Leonid Karlinsky} and {Rogerio Feris} and {Trevor Darrell} and {Roei Herzig}}, year = {2026}, eprint = {2609.02885v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.02885v1}, note = {First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T17:59:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.03438", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.03438"}} @misc{arxiv_2609_03438, title = {{Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents}}, author = {{Zhaoyuan Huang} and {Tianjie Ju} and {Pengzhou Cheng} and {Zheng Wu} and {Yansi Li} and {Chuanbiao Song} and {Jun Lan} and {Huijia Zhu} and {Weiqiang Wang} and {Zhuosheng Zhang}}, year = {2026}, eprint = {2609.03438v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.03438v1}, note = {First published: 2026-09-03; Recorded arXiv version: v1; Recorded version updated: 2026-09-03T06:48:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.04850", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.04850"}} @misc{arxiv_2609_04850, title = {{ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults}}, author = {{Weide Zhan} and {Qumu Shaqu} and {Yuanqing Liu} and {Peng Zhang} and {Jiahao Liu} and {Kam Him Lam} and {Ning Gu} and {Zhan Hu} and {Tun Lu}}, year = {2026}, eprint = {2609.04850v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.04850v1}, note = {First published: 2026-09-04; Recorded arXiv version: v1; Recorded version updated: 2026-09-04T08:09:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.04869", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.04869"}} @misc{arxiv_2609_04869, title = {{From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents}}, author = {{Longtao Hu} and {Xiao Liang} and {Linchao Zhu}}, year = {2026}, eprint = {2609.04869v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.04869v1}, note = {First published: 2026-09-04; Recorded arXiv version: v1; Recorded version updated: 2026-09-04T08:29:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.05374", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.05374"}} @misc{arxiv_2609_05374, title = {{CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents}}, author = {{Haoting Shi} and {Wenhao Wang} and {Weicheng Fang} and {Yaozhong Liang} and {Tian Jin} and {Pengxiang Zhao} and {Guangyi Liu} and {Siheng Chen} and {Yanfeng Wang}}, year = {2026}, eprint = {2609.05374v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.05374v1}, note = {First published: 2026-09-04; Recorded arXiv version: v1; Recorded version updated: 2026-09-04T17:26:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.05511", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.05511"}} @misc{arxiv_2609_05511, title = {{SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction}}, author = {{Bowei He} and {Xiaokun Zhang} and {Meng Ding} and {Xue Liu}}, year = {2026}, eprint = {2609.05511v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.05511v1}, note = {First published: 2026-08-31; Recorded arXiv version: v1; Recorded version updated: 2026-08-31T08:16:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.05513", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.05513"}} @misc{arxiv_2609_05513, title = {{When and What to Teach: Budget-Aware Online Adaptation for Web Agents}}, author = {{Jianwei Zhang} and {Sihan Cao} and {Pengcheng Zheng} and {Ya Wen} and {Pei Ke} and {Kuien Liu} and {Shen Gao} and {Wei Dong} and {Yang Yang} and {Chaoning Zhang}}, year = {2026}, eprint = {2609.05513v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.05513v1}, note = {First published: 2026-08-31; Recorded arXiv version: v1; Recorded version updated: 2026-08-31T08:40:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.06530", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.06530"}} @misc{arxiv_2609_06530, title = {{Selective Knowledge Control for Continual GUI Agent Learning over Application Streams}}, author = {{Zirui Shang} and {Xin Shu} and {Yang Liu} and {Zhi Gao} and {Xinxiao Wu} and {Lifeng Fan}}, year = {2026}, eprint = {2609.06530v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.06530v1}, note = {First published: 2026-09-06; Recorded arXiv version: v1; Recorded version updated: 2026-09-06T10:50:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.06792", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.06792"}} @misc{arxiv_2609_06792, title = {{Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions}}, author = {{Juyong Lee} and {Woogyeol Jin} and {Kimin Lee}}, year = {2026}, eprint = {2609.06792v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.06792v1}, note = {First published: 2026-09-06; Recorded arXiv version: v1; Recorded version updated: 2026-09-06T19:22:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.07712", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.07712"}} @misc{arxiv_2609_07712, title = {{APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents}}, author = {{Jintian Feng} and {Long Chen} and {Xiao Yu} and {Jiayi Dai} and {Chenglong Liu} and {Haoru Wang} and {Zizhen Xue} and {Yuxuan Shi} and {Ziyang Wang} and {Yichen Gong}}, year = {2026}, eprint = {2609.07712v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.07712v1}, note = {First published: 2026-09-07; Recorded arXiv version: v1; Recorded version updated: 2026-09-07T16:25:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.09212", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.09212"}} @misc{arxiv_2609_09212, title = {{AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents}}, author = {{Zhihao Liu} and {Hongyu Sun} and {Zhiyuan Fu} and {Xiaonan Duan} and {Jice Wang} and {Shangru Zhao} and {Weizhi Meng} and {Wuxin Yang} and {Yangfan Zhou} and {Yuqing Zhang}}, year = {2026}, eprint = {2609.09212v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.09212v1}, note = {First published: 2026-09-06; Recorded arXiv version: v1; Recorded version updated: 2026-09-06T03:49:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.10031", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.10031"}} @misc{arxiv_2609_10031, title = {{GraphDroid: Asynchronous LLM-Based Mobile App GUI Testing via History-Aware Exploration and Hybrid Intent Fulfillment}}, author = {{Xiaolei Li} and {Jialun Cao} and {Zhijian Hou} and {Yuzhi Zhao} and {Yepang Liu} and {Shing-Chi Cheung}}, year = {2026}, eprint = {2609.10031v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.10031v1}, note = {First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T11:04:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.10297", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.10297"}} @misc{arxiv_2609_10297, title = {{TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents}}, author = {{Yuhao Wang} and {Mu Qiao} and {Xindong Zhang} and {Yunzhi Zhuge} and {Lei Zhang} and {Huchuan Lu}}, year = {2026}, eprint = {2609.10297v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.10297v1}, note = {First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T15:12:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.10451", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.10451"}} @misc{arxiv_2609_10451, title = {{JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition}}, author = {{Zixiang Chen} and {Yuheng Lu} and {Zihao Cheng} and {Zeming Liu} and {Jizeng Bai} and {Ziye Huang} and {Zhiyin Lin} and {Zihan Li} and {Yuhang Guo} and {Yunhong Wang} and {Haifeng Wang}}, year = {2026}, eprint = {2609.10451v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.10451v1}, note = {First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T16:59:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.12394", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.12394"}} @misc{arxiv_2609_12394, title = {{BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents}}, author = {{Tong Ye} and {Kunyang Han} and {Guozhi Wang} and {Longqiang Luo} and {Zhifeng Ding} and {Yongxiang Zhang} and {Xiaolei Shen} and {Yuxuan Zhang} and {Zhuping Zhang} and {Tao Xu} and {Yue Pan} and {Yucheng Zhao} and {Yupei Hu} and {Yuanjiang Ouyang} and {Danfeng Shen} and {Runqi Lin} and {Hongda Cai} and {Zhaoxiong Wang} and {Mengjia Yan} and {Yingjie Zhong} and {Chen Zhou} and {Zeyu Zhang} and {Xuwen Zhu} and {Penggang Shi} and {Mingcheng Luo} and {Ziyang Wu} and {Min Jin} and {Mingfu Shen} and {Zairong Xu} and {Fan Zhang} and {Hao Wang} and {Liang Liu} and {Zhulin Xie} and {Lijun Yao} and {Xiao Liang} and {Liangmin Wen} and {Liqiang Feng} and {Feilong Wu} and {Min Hu} and {Min Chen} and {Guanjing Xiong} and {Xiaohu Ruan} and {Xiaoxin Chen}}, year = {2026}, eprint = {2609.12394v3}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.12394v3}, note = {First published: 2026-09-11; Recorded arXiv version: v3; Recorded version updated: 2026-09-15T06:36:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.13287", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.13287"}} @misc{arxiv_2609_13287, title = {{LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents}}, author = {{Zhangxuan Gu} and {Haoxing Chen} and {Qi Qin} and {Yi Xin} and {Kai Gan} and {Lin Liu} and {Long Cui} and {Xiaomei Wang} and {Beitong Zhou} and {Yunzhu Zhang} and {Zhengwen Zeng} and {Changlong Gao} and {Weizhi Chen} and {Rongchao Zhang} and {Haoyuan Wu} and {Shuheng Shen} and {Changhua Meng} and {Weiqiang Wang} and {Jianguo Li} and {Zhenzhong Lan}}, year = {2026}, eprint = {2609.13287v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.13287v1}, note = {First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T05:53:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.13491", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.13491"}} @misc{arxiv_2609_13491, title = {{Token Efficient Task Execution via Application Behavior Modeling for Web Agents}}, author = {{Alexandru Ianta} and {Eleni Stroulia}}, year = {2026}, eprint = {2609.13491v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.13491v1}, note = {First published: 2026-09-11; Recorded arXiv version: v1; Recorded version updated: 2026-09-11T19:57:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.13548", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.13548"}} @misc{arxiv_2609_13548, title = {{AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents}}, author = {{Xinyun Cao} and {Adriana Szekeres} and {Fazle Elahi Faisal}}, year = {2026}, eprint = {2609.13548v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.13548v1}, note = {First published: 2026-09-11; Recorded arXiv version: v1; Recorded version updated: 2026-09-11T21:24:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.13873", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.13873"}} @misc{arxiv_2609_13873, title = {{PriMobiBench: Characterizing Visual Privacy Leakage in VLM-Driven Mobile GUI Agents}}, author = {{Qihang Cen} and {Tianshuo Cong} and {Da Song} and {Xinlei He} and {Jiaxing Song} and {Ke Xu} and {Qi Li}}, year = {2026}, eprint = {2609.13873v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.13873v1}, note = {First published: 2026-09-12; Recorded arXiv version: v1; Recorded version updated: 2026-09-12T10:55:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.15307", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.15307"}} @misc{arxiv_2609_15307, title = {{Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding}}, author = {{Yizhou Liu} and {Fei Tang} and {Yuchen Yan} and {Zhengxi Lu} and {Songqin Nong} and {Tao Jiang} and {Wenhao Xu} and {Wenqi Zhang} and {Weiming Lu} and {Jun Xiao} and {Yongliang Shen}}, year = {2026}, eprint = {2609.15307v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.15307v1}, note = {First published: 2026-09-14; Recorded arXiv version: v1; Recorded version updated: 2026-09-14T09:56:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.15457", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.15457"}} @misc{arxiv_2609_15457, title = {{AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation}}, author = {{Shengjie Jin} and {Zelong Sun} and {Hengbo Xu} and {Yanbiao Ma} and {Zhiwu Lu}}, year = {2026}, eprint = {2609.15457v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.15457v1}, note = {First published: 2026-09-14; Recorded arXiv version: v1; Recorded version updated: 2026-09-14T12:22:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.16251", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.16251"}} @misc{arxiv_2609_16251, title = {{CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design}}, author = {{Zihan Dong} and {Yuanzhe Liu} and {Zhiyuan Ma} and {Qishi Zhan} and {Dehan Kong} and {Guohao Li} and {Kaixin Li}}, year = {2026}, eprint = {2609.16251v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.16251v2}, note = {First published: 2026-09-14; Recorded arXiv version: v2; Recorded version updated: 2026-09-21T14:30:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.16635", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.16635"}} @misc{arxiv_2609_16635, title = {{EchoPath: Execution-Level Replayable Memory for GUI Agents}}, author = {{Yao Zhao} and {Aditya Shanmugham} and {Swastik Roy} and {Yanxun Xu}}, year = {2026}, eprint = {2609.16635v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.16635v1}, note = {First published: 2026-09-15; Recorded arXiv version: v1; Recorded version updated: 2026-09-15T04:56:17Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.16732", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.16732"}} @misc{arxiv_2609_16732, title = {{When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents}}, author = {{Heng Li} and {Fulin Zhao} and {Zhe Geng} and {Zhiyuan Yao} and {Wei Yuan} and {Xiapu Luo}}, year = {2026}, eprint = {2609.16732v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.16732v1}, note = {First published: 2026-09-15; Recorded arXiv version: v1; Recorded version updated: 2026-09-15T07:02:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.17653", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.17653"}} @misc{arxiv_2609_17653, title = {{Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents}}, author = {{Bofan Chen} and {Boxuan Zhang} and {Fei Tang} and {Zhengxi Lu} and {Yong Du} and {Tongbo Chen} and {Weiming Lu} and {Jun Xiao} and {Yueting Zhuang} and {Yongliang Shen}}, year = {2026}, eprint = {2609.17653v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.17653v1}, note = {First published: 2026-09-15; Recorded arXiv version: v1; Recorded version updated: 2026-09-15T17:24:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.17885", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.17885"}} @misc{arxiv_2609_17885, title = {{ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software}}, author = {{Kratika Bhagtani} and {Kusha Sridhar} and {Maziyar Baran Pouyan} and {Yuying Zhao} and {Eugene Siow}}, year = {2026}, eprint = {2609.17885v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.17885v2}, note = {First published: 2026-09-15; Recorded arXiv version: v2; Recorded version updated: 2026-09-23T01:31:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.18690", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.18690"}} @misc{arxiv_2609_18690, title = {{RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection}}, author = {{Liyang Fan} and {Xinping Bi} and {Yitai Li} and {Shuaimin Li} and {Hui Li} and {Min Yang}}, year = {2026}, eprint = {2609.18690v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.18690v1}, note = {First published: 2026-09-16; Recorded arXiv version: v1; Recorded version updated: 2026-09-16T14:06:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.19523", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.19523"}} @misc{arxiv_2609_19523, title = {{EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data}}, author = {{Yinzhu Quan} and {Zefang Liu}}, year = {2026}, eprint = {2609.19523v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.19523v2}, note = {First published: 2026-09-17; Recorded arXiv version: v2; Recorded version updated: 2026-10-08T04:53:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.19843", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.19843"}} @misc{arxiv_2609_19843, title = {{A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents}}, author = {{Haya Halimeh} and {Sascha Kaltenpoth} and {Kevin Bösch} and {Oliver Müller}}, year = {2026}, eprint = {2609.19843v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.19843v1}, note = {First published: 2026-09-17; Recorded arXiv version: v1; Recorded version updated: 2026-09-17T07:54:15Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.22000", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.22000"}} @misc{arxiv_2609_22000, title = {{RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents}}, author = {{Shuai Bai} and {Jiayong Deng} and {Sicheng Fan} and {Yikun Fu} and {Chang Gao} and {Xuhao Hu} and {Mianqiu Huang} and {Yizhen Jiang} and {Yuheng Jing} and {Dehui Kong} and {Keliang Li} and {Ning Li} and {Wanli Li} and {Dayiheng Liu} and {Dunjie Lu} and {Changwei Luo} and {Que Shen} and {Zheyuan Wang} and {Zijian Wang} and {Jie Wu} and {Gao Wu} and {Zhihui Xie} and {Rui Xie} and {Haiyang Xu} and {An Yang} and {Jiakang Yuan} and {Yanming Zhang} and {Jiajun Zhang} and {Xi Zhang} and {Zhenru Zhang} and {Zhuo Zhen} and {Mingkang Zhu} and {Bowen Zhou}}, year = {2026}, eprint = {2609.22000v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.22000v2}, note = {First published: 2026-09-18; Recorded arXiv version: v2; Recorded version updated: 2026-09-21T07:09:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.22083", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.22083"}} @misc{arxiv_2609_22083, title = {{MintAct: A Unified Visual Agent for Digital Environments}}, author = {{Mingfei Gao} and {Rui Tian} and {Haiming Gang} and {Bohan Zhai} and {Le Zhang} and {Yuanzheng Gong} and {Di Feng} and {Ege Özsoy} and {Kaixin Ma} and {Vishwesh Kirthivasan} and {Oğuzhan Fatih Kar} and {Roman Bachmann} and {Anders Boesen Lindbo Larsen} and {Afshin Dehghan}}, year = {2026}, eprint = {2609.22083v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.22083v1}, note = {First published: 2026-09-18; Recorded arXiv version: v1; Recorded version updated: 2026-09-18T17:59:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.22178", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.22178"}} @misc{arxiv_2609_22178, title = {{Beyond Task Completion: Training Capable and Safe Computer-Use Agents}}, author = {{Zeyu Kang} and {Zhenyun Yin} and {Yang Zhang} and {Shan He} and {Shanzhe Lei} and {Yanjiu Zhong} and {Xinquan Chen} and {Xuhong Wang}}, year = {2026}, eprint = {2609.22178v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.22178v2}, note = {First published: 2026-08-27; Recorded arXiv version: v2; Recorded version updated: 2026-09-22T06:39:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.24277", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.24277"}} @misc{arxiv_2609_24277, title = {{How Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation}}, author = {{Yunxiang Li} and {Xixin Wu} and {Helen Meng}}, year = {2026}, eprint = {2609.24277v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.24277v1}, note = {First published: 2026-09-21; Recorded arXiv version: v1; Recorded version updated: 2026-09-21T08:42:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.24890", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.24890"}} @misc{arxiv_2609_24890, title = {{OSWorld-Pro: Process-based Evaluation for Computer Use Agents}}, author = {{Zhilin Wang} and {Shaokun Zhang} and {Yifan Zhang} and {Hao Zhang} and {Jin Xu} and {Binfeng Xu} and {Jian Hu} and {Yunheng Zou} and {Karan Sapra} and {Andrew Tao} and {Jan Kautz} and {Yi Dong}}, year = {2026}, eprint = {2609.24890v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.24890v1}, note = {First published: 2026-09-21; Recorded arXiv version: v1; Recorded version updated: 2026-09-21T16:55:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.25769", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.25769"}} @misc{arxiv_2609_25769, title = {{Towards Omni-dimensional GUI Agent Navigation with Masked Trajectory Prediction}}, author = {{Yan Zhang} and {Pei Fu} and {Daiqing Wu} and {Huawen Shen} and {Ruoceng Zhang} and {Shaojie Zhang} and {Jiahui Yang} and {Yu Zhou} and {Can Ma} and {Zhenbo Luo} and {Jian Luan}}, year = {2026}, eprint = {2609.25769v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.25769v1}, note = {First published: 2026-09-22; Recorded arXiv version: v1; Recorded version updated: 2026-09-22T07:02:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.27273", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.27273"}} @misc{arxiv_2609_27273, title = {{CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments}}, author = {{Yuxuan Li} and {Will Epperson} and {Wesley Deng} and {Zezhou Huang}}, year = {2026}, eprint = {2609.27273v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.27273v2}, note = {First published: 2026-09-23; Recorded arXiv version: v2; Recorded version updated: 2026-09-27T20:49:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.27307", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.27307"}} @misc{arxiv_2609_27307, title = {{Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents}}, author = {{Yan Zhang} and {Daiqing Wu} and {Huawen Shen} and {Liang Li} and {Gang Cao} and {Zhi Gong} and {Wei Dai} and {Xiaode Zhang} and {Can Ma} and {Yu Zhou}}, year = {2026}, eprint = {2609.27307v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.27307v1}, note = {First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T03:38:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.27353", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.27353"}} @misc{arxiv_2609_27353, title = {{Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents}}, author = {{Chengguang Gan} and {Yunhao Liang} and {QingHao Zhang} and {Shiwen Ni}}, year = {2026}, eprint = {2609.27353v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.27353v1}, note = {First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T04:49:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.27461", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.27461"}} @misc{arxiv_2609_27461, title = {{Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents}}, author = {{Zeyu Zhang} and {Dingyi Rong} and {Zijian Chen} and {Zicheng Zhang} and {Xiongkuo Min} and {Guangtao Zhai}}, year = {2026}, eprint = {2609.27461v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.27461v1}, note = {First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T07:27:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.27770", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.27770"}} @misc{arxiv_2609_27770, title = {{Improving LLM-based Autonomous Web Agents with Filtering}}, author = {{Zhitong Guo} and {Jing Yu Koh} and {Ruiyu Li}}, year = {2026}, eprint = {2609.27770v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.27770v1}, note = {First published: 2026-08-16; Recorded arXiv version: v1; Recorded version updated: 2026-08-16T19:54:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.29892", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.29892"}} @misc{arxiv_2609_29892, title = {{Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents}}, author = {{Tingyu Qu} and {Weigao Sun} and {Yuecheng Liu} and {Yucheng Zhao} and {Yi Zhu} and {Yifeng Ding} and {Qiyi Wang} and {Sihan Cao} and {Pengkun Jiao} and {Hanlei Xie} and {Xiongwei Wu} and {Qichao Wang} and {Haodong Zhang} and {Jiajun Liu} and {Yuhao Wang} and {Yuqing Xie} and {Junpeng Zhao} and {Long Chen} and {Ming Ma} and {Sihan Yang} and {Ziwang Zhao} and {Yanhao Jia} and {Liangquan Gong} and {Feida Zhu} and {Yiran Zhong} and {Steven Hoi}}, year = {2026}, eprint = {2609.29892v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.29892v1}, note = {First published: 2026-09-24; Recorded arXiv version: v1; Recorded version updated: 2026-09-24T14:38:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.30186", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.30186"}} @misc{arxiv_2609_30186, title = {{Jev-Mobile: Jev as an Executor for Mobile GUI Agents}}, author = {{Linghua Zhang}}, year = {2026}, eprint = {2609.30186v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.30186v1}, note = {First published: 2026-09-24; Recorded arXiv version: v1; Recorded version updated: 2026-09-24T17:30:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.30604", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.30604"}} @misc{arxiv_2609_30604, title = {{The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge}}, author = {{Alexander Gill} and {Md Farhan Ishmam} and {Xuyen Nguyen} and {Neha Bhat} and {Parker Henry DeYoung} and {Fateme Hashemi Chaleshtori} and {Nathan Stringham} and {Kenneth Marino} and {Ana Marasović}}, year = {2026}, eprint = {2609.30604v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.30604v1}, note = {First published: 2026-09-24; Recorded arXiv version: v1; Recorded version updated: 2026-09-24T22:36:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.30887", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.30887"}} @misc{arxiv_2609_30887, title = {{From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks}}, author = {{Yuchen Sun} and {Chenglin Cai} and {Gongjie Zhang} and {Tianyu Xia} and {Quyu Kong} and {Panrong Tong} and {Zhengwen Zeng} and {Long Chen} and {Steven Hoi} and {Chongyang Zhang} and {Yue Wang}}, year = {2026}, eprint = {2609.30887v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.30887v1}, note = {First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T06:50:04Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.31364", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2609.31364"}} @misc{arxiv_2609_31364, title = {{OpenVAM: Open-World Visual Attention Modeling with VLMs}}, author = {{Kiana Hooshanfar} and {Amirhossein Kazerouni} and {Alireza Hosseini} and {Michael Brudno} and {Babak Taati}}, year = {2026}, eprint = {2609.31364v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.31364v1}, note = {First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T14:59:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.31957", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.31957"}} @misc{arxiv_2609_31957, title = {{CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs}}, author = {{Zhenhao Zhang} and {Zhaoyu Fan} and {Haohan Ying} and {Jingwen Hu} and {Hancen Fan} and {Junhao Zhou} and {Zitian Chen} and {Linchao Zhu}}, year = {2026}, eprint = {2609.31957v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.31957v1}, note = {First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T20:04:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32036", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32036"}} @misc{arxiv_2609_32036, title = {{ScreenHaystack: Finding Blind Zones in GUI Grounding}}, author = {{Chenyue Li} and {Xiaoxiao Sun} and {Yubo Deng} and {Qinlin Zhao} and {Serena Yeung-Levy} and {Yuhui Zhang}}, year = {2026}, eprint = {2609.32036v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32036v1}, note = {First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T22:07:29Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32130", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32130"}} @misc{arxiv_2609_32130, title = {{REBASE: Device-Cloud Experience Coherence for GUI Agents Across App Updates}}, author = {{Beining Wu} and {Jun Huang} and {Yanxiao Zhao}}, year = {2026}, eprint = {2609.32130v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32130v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T01:13:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32166", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32166"}} @misc{arxiv_2609_32166, title = {{PastForward: Faster On-Device GUI Agents via Computational Experience Reuse}}, author = {{Taehwan Park} and {Changmin Lee} and {Hayeon Lee} and {Taesik Gong}}, year = {2026}, eprint = {2609.32166v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32166v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T02:41:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32351", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32351"}} @misc{arxiv_2609_32351, title = {{From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs}}, author = {{Yangzhe Peng} and {Xiaoyang Wang} and {Yiyang Zhao} and {Lijun Wu} and {Kun He}}, year = {2026}, eprint = {2609.32351v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32351v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T08:14:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32385", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32385"}} @misc{arxiv_2609_32385, title = {{DashAct: A Progressive Diagnostic Benchmark for GUI Agents in Interactive Dashboard Analysis}}, author = {{Chuhan Zhang} and {Qi Xie} and {Ziyue Wang} and {Jianing Yin} and {Yunfan Zhou} and {Dazhen Deng} and {Yingcai Wu}}, year = {2026}, eprint = {2609.32385v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32385v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T08:58:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32511", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32511"}} @misc{arxiv_2609_32511, title = {{Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents}}, author = {{Jinming Hu} and {Haodong Zhao} and {Qi Jia} and {Die Chen} and {Tianhang Zhao} and {Sufeng Duan} and {Gongshen Liu}}, year = {2026}, eprint = {2609.32511v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32511v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T11:59:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32600", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32600"}} @misc{arxiv_2609_32600, title = {{CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering}}, author = {{Prince Zizhuang Wang} and {Chenhao Liang} and {Zelong Xu} and {Aojie Yuan} and {Xiaolin Zhou} and {Haiyue Zhang} and {Yue Zhao} and {Xiyang Hu} and {Shuli Jiang}}, year = {2026}, eprint = {2609.32600v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32600v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T13:18:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32679", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32679"}} @misc{arxiv_2609_32679, title = {{The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models}}, author = {{Dongsheng Liu} and {Chao Jin} and {Wenkui Yang} and {Hejin Wang} and {Junwei Yang} and {Zeren Zhang} and {Ziwei Chen} and {Huaibo Huang} and {Jie Cao} and {Ran He}}, year = {2026}, eprint = {2609.32679v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32679v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T14:35:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32750", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32750"}} @misc{arxiv_2609_32750, title = {{CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning}}, author = {{Xin Yan} and {Zhengbo Jiao} and {Jiaqi Liu} and {Zhenglin Wan} and {SiYuan Ma} and {Xuliang Yu} and {Tianyi Jiang} and {Chubin Zhang} and {Pengfei Zhou} and {Wangbo Zhao} and {Xingrui Yu} and {Bo An} and {Yang You} and {Ivor Tsang}}, year = {2026}, eprint = {2609.32750v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32750v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T16:16:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.32915", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32915"}} @misc{arxiv_2609_32915, title = {{AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents}}, author = {{Asif Shahriar} and {Md Nafiu Rahman} and {Sadif Ahmed} and {Farig Sadeque} and {Md Rizwan Parvez}}, year = {2026}, eprint = {2609.32915v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.32915v1}, note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T20:09:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.33102", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.33102"}} @misc{arxiv_2609_33102, title = {{ORBIT: A Framework for Multi-Agent Safety and Security Evaluations}}, author = {{Ben Hagag} and {William L. Anderson} and {Srija Chakraborty} and {Christian Schroeder de Witt}}, year = {2026}, eprint = {2609.33102v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.33102v1}, note = {First published: 2026-09-27; Recorded arXiv version: v1; Recorded version updated: 2026-09-27T02:20:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.33304", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.33304"}} @misc{arxiv_2609_33304, title = {{Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents}}, author = {{Fuyao Zhang} and {Xuan Wang} and {Zherui Li} and {Jiaming Zhang} and {Longtao Huang} and {Wei Yang Bryan Lim}}, year = {2026}, eprint = {2609.33304v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.33304v1}, note = {First published: 2026-09-27; Recorded arXiv version: v1; Recorded version updated: 2026-09-27T07:15:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.33646", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.33646"}} @misc{arxiv_2609_33646, title = {{Probe to Act: Elevating Browser-Use Agent via Active Visual Probing}}, author = {{Keliang Li} and {Heng Wang} and {Chen Hu} and {Daxin Jiang} and {Hong Chang} and {Shiguang Shan}}, year = {2026}, eprint = {2609.33646v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.33646v1}, note = {First published: 2026-09-27; Recorded arXiv version: v1; Recorded version updated: 2026-09-27T15:11:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.34113", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.34113"}} @misc{arxiv_2609_34113, title = {{GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions}}, author = {{Shaoqing Zhang} and {Kehai Chen} and {Xuefeng Bai} and {Zhuosheng Zhang} and {Pengfei Zhang} and {Yang Xiang} and {Min Zhang}}, year = {2026}, eprint = {2609.34113v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.34113v2}, note = {First published: 2026-09-28; Recorded arXiv version: v2; Recorded version updated: 2026-09-29T09:05:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.34139", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.34139"}} @misc{arxiv_2609_34139, title = {{Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize?}}, author = {{Tien Tran} and {Namho Koh} and {Daiki E. Matsunaga} and {Ayush Jain} and {Kee Eung Kim}}, year = {2026}, eprint = {2609.34139v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.34139v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T02:21:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.34321", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.34321"}} @misc{arxiv_2609_34321, title = {{One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents}}, author = {{Ziqiang Wang} and {Li Gu} and {Zhixiang Chi} and {Linlian Jiang} and {Zihuan Jiang} and {Linqiang Guo} and {Siobhan Reid} and {Zhi Liu} and {Yang Wang}}, year = {2026}, eprint = {2609.34321v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.34321v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T05:00:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.34769", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2609.34769"}} @misc{arxiv_2609_34769, title = {{LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles}}, author = {{Bingo Zhang} and {Haochuan Lu} and {Zongjie Li} and {Genjian Li} and {Ari Yu Zhang} and {Chaozheng Wang}}, year = {2026}, eprint = {2609.34769v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.34769v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T09:49:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.34974", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.34974"}} @misc{arxiv_2609_34974, title = {{Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces}}, author = {{Ruozhao Yang} and {Mingfei Cheng} and {Xiaofei Xie}}, year = {2026}, eprint = {2609.34974v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.34974v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T11:53:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.35026", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.35026"}} @misc{arxiv_2609_35026, title = {{WebPageBench: Event-Level Verification and Controlled UI-Variant Generation for Web Agents}}, author = {{Anton Emelyanov} and {Maria Tikhonova} and {Zaven Martirosian} and {Sergei Averkiev} and {Alena Fenogenova}}, year = {2026}, eprint = {2609.35026v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.35026v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T12:24:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.35671", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.35671"}} @misc{arxiv_2609_35671, title = {{PhoneCLI: From App Interfaces to Callable Commands for Mobile Agents}}, author = {{Yangqin Jiang} and {Lingrui Xu} and {Chao Huang}}, year = {2026}, eprint = {2609.35671v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.35671v2}, note = {First published: 2026-09-28; Recorded arXiv version: v2; Recorded version updated: 2026-10-05T01:08:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.35814", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.35814"}} @misc{arxiv_2609_35814, title = {{Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions}}, author = {{Xunjian Yin} and {Tianchen Guan} and {Jinao Wang} and {Weili Cao} and {Daisy Xinlei Lin} and {Royce Cheng-Yue} and {Keagan Long} and {Kyle Wong} and {Bhuwan Dhingra} and {Xiangjun Wang} and {Shuyan Zhou}}, year = {2026}, eprint = {2609.35814v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.35814v1}, note = {First published: 2026-09-20; Recorded arXiv version: v1; Recorded version updated: 2026-09-20T16:16:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.35904", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.35904"}} @misc{arxiv_2609_35904, title = {{Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge}}, author = {{Ziqi Zhang} and {Shaohui Li} and {Bing Li}}, year = {2026}, eprint = {2609.35904v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.35904v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T04:02:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.36201", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.36201"}} @misc{arxiv_2609_36201, title = {{SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety}}, author = {{Jianxing Chen} and {Xiao Yu} and {Shipra Agrawal} and {Zhou Yu}}, year = {2026}, eprint = {2609.36201v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.36201v1}, note = {First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T20:01:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.36488", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.36488"}} @misc{arxiv_2609_36488, title = {{AdaptArena: Evaluating Test-Time Personalization of Web Agents}}, author = {{Dongchan Shin} and {Xing Han Lù} and {Jiaqi Deng} and {Jay Gala} and {Tomás Vergara Browne} and {Jaewon Moon} and {Fengyuan Liu} and {Alexandre Drouin} and {Siva Reddy} and {Alexandre Lacoste}}, year = {2026}, eprint = {2609.36488v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.36488v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T01:46:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.36923", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.36923"}} @misc{arxiv_2609_36923, title = {{PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval}}, author = {{Bin Kang} and {Jiarui Ouyang} and {Li Jiang} and {Bin Chen} and {Zhuotao Tian}}, year = {2026}, eprint = {2609.36923v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.36923v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T07:41:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.36927", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.36927"}} @misc{arxiv_2609_36927, title = {{Neuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution}}, author = {{Hyewon Suh} and {Thanh Minh Nguyen} and {Chih-Lun Lee} and {Darrow Hartman} and {Lizhao Liu} and {Xin Eric Wang} and {Ang Li} and {Jiachen Yang}}, year = {2026}, eprint = {2609.36927v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.36927v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T07:44:22Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.36939", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.36939"}} @misc{arxiv_2609_36939, title = {{SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents}}, author = {{Shengtian Yang} and {Ziyu Xiong} and {Kaibing Yang} and {Guangfeng Cai} and {Yewen Li} and {Peng Jiang} and {Gai Kun} and {Qingpeng Cai} and {Lei Feng}}, year = {2026}, eprint = {2609.36939v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.36939v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T07:51:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.37053", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.37053"}} @misc{arxiv_2609_37053, title = {{MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows}}, author = {{Mei Wu} and {Rui Xie} and {Runyu Zhang} and {Yuqiang Li} and {Tianfan Fu} and {Bo Chen} and {Kai Yu} and {Xin Chen} and {Lu Chen}}, year = {2026}, eprint = {2609.37053v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.37053v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T08:58:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.37176", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.37176"}} @misc{arxiv_2609_37176, title = {{Absorbed in Inertia: Activation Analysis for Computer-Use Agents}}, author = {{Giulio Segalini} and {Zhi Wen Soi} and {Jérémie Decouchant} and {Lydia Chen}}, year = {2026}, eprint = {2609.37176v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.37176v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T10:01:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.37686", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.37686"}} @misc{arxiv_2609_37686, title = {{EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?}}, author = {{Hongcheng Gao} and {Hailong Qu} and {Yu Lei} and {Henghui Sun} and {Haoyang Li} and {Yipeng Wei} and {Naihao Xue} and {Xiaohan Yu} and {Zhuo Tao} and {Yihe Zang} and {Yajiao Wang} and {Jingyi Tang} and {Yi Li} and {Jingjing Zhou} and {Jie Luo} and {Bohan Zeng} and {Chengyu Shen} and {Hao Jiang} and {Chong Chen} and {Bowen Qu} and {Olive Huang} and {Zeqiang Wang}}, year = {2026}, eprint = {2609.37686v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.37686v2}, note = {First published: 2026-09-29; Recorded arXiv version: v2; Recorded version updated: 2026-10-09T08:15:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.38008", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.38008"}} @misc{arxiv_2609_38008, title = {{HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents}}, author = {{Tongbo Chen} and {Junbo Niu} and {Zhengxi Lu} and {Niu Lian} and {Fei Tang} and {Yuchen Yan} and {Yike Hong} and {Yong Du} and {Yizhou Liu} and {Bofan Chen} and {Yongliang Shen}}, year = {2026}, eprint = {2609.38008v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.38008v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T16:57:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.38184", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.38184"}} @misc{arxiv_2609_38184, title = {{RealGUINoise: An Interactive Cross-Platform Benchmark for GUI Agent Robustness under Real-World Interface Noise}}, author = {{Yongjiang Wu} and {Junyuan Zhang} and {Ada Chen} and {Kuiyi Gao} and {Wenxuan Wang}}, year = {2026}, eprint = {2609.38184v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.38184v1}, note = {First published: 2026-08-07; Recorded arXiv version: v1; Recorded version updated: 2026-08-07T07:51:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.38778", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.38778"}} @misc{arxiv_2609_38778, title = {{Action Conditioned Bisimulation For GUI Agent Memory}}, author = {{Hongbo Zhang} and {Liuyang Song} and {Quanquan Li} and {Daqian Yang} and {Yan Wen} and {Zhengtao Yao}}, year = {2026}, eprint = {2609.38778v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.38778v1}, note = {First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T02:11:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.38867", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.38867"}} @misc{arxiv_2609_38867, title = {{Talk2Agent: Benchmarking Voice Interfaces for Text Agents}}, author = {{Terumi Chiba} and {Guangzhi Sun} and {Zheqi Yuan} and {Chao Zhang}}, year = {2026}, eprint = {2609.38867v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.38867v1}, note = {First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T03:19:25Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.39547", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.39547"}} @misc{arxiv_2609_39547, title = {{Learning Reliable GUI Agents under Imperfect Priors}}, author = {{Bo Han} and {Qianyi Wang} and {Shuai Liu} and {Xiong Zifan} and {Changqiao Wu} and {Yuanfa Li} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Heng Qu} and {Yunpeng Song} and {Zhongmin Cai}}, year = {2026}, eprint = {2609.39547v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.39547v1}, note = {First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T11:45:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.39903", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.39903"}} @misc{arxiv_2609_39903, title = {{OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software}}, author = {{Dingyuan Dai} and {Heli Qi} and {Lei Liu} and {Yinxi Li} and {Baiding Chen} and {Zijun Dou} and {Qingcheng Zeng} and {Qi Kang} and {Oliver Sun} and {Eric Wang} and {Bo Zhou} and {Haixin Wang} and {Yufan Du} and {Shi Bo} and {Ruihan Lin} and {Mengqi Yuan} and {Dunjie Lu} and {Steven Dillmann} and {Yiming Shi} and {Tina Su} and {Amy Xin} and {Minghao Liu} and {Xi Wang} and {Xu Huang} and {Ge Zhang} and {Pengyu Nie} and {Zhen Yang} and {Jie Tang} and {Juanzi Li} and {Weihao Xuan} and {Tianyu Liu}}, year = {2026}, eprint = {2609.39903v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.39903v1}, note = {First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T15:03:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.40253", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.40253"}} @misc{arxiv_2609_40253, title = {{ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents}}, author = {{Yong Du} and {Tongbo Chen} and {Zhengxi Lu} and {Yizhou Liu} and {Bofan Chen} and {Tao Jiang} and {Wenhao Xu} and {Yongliang Shen}}, year = {2026}, eprint = {2609.40253v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.40253v2}, note = {First published: 2026-09-30; Recorded arXiv version: v2; Recorded version updated: 2026-10-01T17:50:14Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2609.40284", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.40284"}} @misc{arxiv_2609_40284, title = {{cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents}}, author = {{Pranjal Aggarwal} and {Lawrence Keunho Jang} and {Sean Welleck} and {Daniel Fried} and {Ruslan Salakhutdinov} and {Jing Yu Koh}}, year = {2026}, eprint = {2609.40284v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.40284v1}, note = {First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T17:48:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.00948", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.00948"}} @misc{arxiv_2610_00948, title = {{GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution}}, author = {{Geyi Yang} and {Zikun Qu} and {Xiang Li} and {Zhiyong Wang} and {Min Zhang} and {Shipei Zeng} and {Zhongxiang Dai}}, year = {2026}, eprint = {2610.00948v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.00948v1}, note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T02:31:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.01215", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.01215"}} @misc{arxiv_2610_01215, title = {{AutoGUIWorld: Image Generators as Visual World Models for GUI Agent}}, author = {{Cheng Yang} and {Yifan Wu} and {Yutao Huang} and {Zhaohua Zhang} and {Beiduo Chen} and {Muxi Chen} and {Chenchen Zhao} and {Hexuan Deng} and {Haolin Yang} and {Geyuan Zhu} and {Sa Zhu} and {Jianhuan Zhuo} and {Qiuyong Xiao} and {Jianhao Ruan} and {Yiran Peng} and {Jiayi Zhang} and {Tian Ye} and {Xinlei Yu} and {Tianwen Jiang} and {Jihong Zhang} and {Yuyu Luo}}, year = {2026}, eprint = {2610.01215v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.01215v1}, note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T07:22:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.01491", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.01491"}} @misc{arxiv_2610_01491, title = {{Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories}}, author = {{Chengguang Gan} and {Zimeng He} and {Yoshihiro Tsujii} and {Ken-ichiro Kobayashi} and {Hiroki Itoh} and {Kotaro Funakoshi}}, year = {2026}, eprint = {2610.01491v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.01491v1}, note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T11:31:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.01787", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.01787"}} @misc{arxiv_2610_01787, title = {{Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents}}, author = {{Beining Wu} and {Zihao Ding} and {Jun Huang}}, year = {2026}, eprint = {2610.01787v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.01787v1}, note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T14:34:32Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.02320", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.02320"}} @misc{arxiv_2610_02320, title = {{DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents}}, author = {{A. Said Gurbuz} and {Ahmed Nassar} and {Sunghwan Hong} and {Marc Pollefeys} and {Peter W. J. Staar}}, year = {2026}, eprint = {2610.02320v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.02320v1}, note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T18:00:05Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.02542", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.02542"}} @misc{arxiv_2610_02542, title = {{How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling}}, author = {{Dhananjay Ashok} and {Shantanu Agarwal} and {Vivek Datla} and {Jonathan May} and {Alfy Samuel}}, year = {2026}, eprint = {2610.02542v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.02542v1}, note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T22:30:08Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.02617", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.02617"}} @misc{arxiv_2610_02617, title = {{WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness}}, author = {{Yun-Yun Tsai} and {Yuning Mao} and {Shiqi Wang} and {Junfeng Yang} and {Sinong Wang}}, year = {2026}, eprint = {2610.02617v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.02617v1}, note = {First published: 2026-10-02; Recorded arXiv version: v1; Recorded version updated: 2026-10-02T00:17:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.02932", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.02932"}} @misc{arxiv_2610_02932, title = {{When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency}}, author = {{Yulong Ming} and {Jie Xu} and {Zihan Wu} and {Xiaohua Jia}}, year = {2026}, eprint = {2610.02932v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.02932v1}, note = {First published: 2026-10-02; Recorded arXiv version: v1; Recorded version updated: 2026-10-02T07:22:46Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.03036", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.03036"}} @misc{arxiv_2610_03036, title = {{WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites}}, author = {{Jiangang Han}}, year = {2026}, eprint = {2610.03036v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.03036v2}, note = {First published: 2026-10-02; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T13:46:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.03089", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.03089"}} @misc{arxiv_2610_03089, title = {{Securing Computer-Use Agents Against Branch Steering Attacks}}, author = {{Giulio Zingrillo} and {Hanna Foerster} and {Ilia Shumailov} and {Yiren Zhao} and {Robert Mullins}}, year = {2026}, eprint = {2610.03089v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.03089v1}, note = {First published: 2026-10-02; Recorded arXiv version: v1; Recorded version updated: 2026-10-02T10:08:39Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.03818", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.03818"}} @misc{arxiv_2610_03818, title = {{Control OSWorld: An AI Control Environment for GUI Computer Use Agents}}, author = {{Maria Sanchez del Rio} and {Mikhail Terekhov}}, year = {2026}, eprint = {2610.03818v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.03818v2}, note = {First published: 2026-10-02; Recorded arXiv version: v2; Recorded version updated: 2026-10-12T23:17:28Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.04116", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.04116"}} @misc{arxiv_2610_04116, title = {{CUAWright: A Minimal Unified Interface for Digital Agents}}, author = {{Yadong Lu} and {Theodore Lee} and {Yifei Li} and {Lawrence Keunho Jang} and {Tianci Xue} and {Yu Su} and {Huan Sun} and {Ahmed Hassan Awadallah}}, year = {2026}, eprint = {2610.04116v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.04116v1}, note = {First published: 2026-10-02; Recorded arXiv version: v1; Recorded version updated: 2026-10-02T22:43:06Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.04800", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.04800"}} @misc{arxiv_2610_04800, title = {{MedImageOSWorld: Benchmarking GUI Agents for Medical Image Consoles}}, author = {{Ziyang Long} and {Xinqi Li} and {Lujing Xing} and {Hsin-Jung Yang}}, year = {2026}, eprint = {2610.04800v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.04800v1}, note = {First published: 2026-10-03; Recorded arXiv version: v1; Recorded version updated: 2026-10-03T22:56:09Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.05185", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.05185"}} @misc{arxiv_2610_05185, title = {{Recurrent Latent Visual Search for GUI Grounding}}, author = {{Kaiyu Wu} and {Beichen Zheng} and {Weiyao Huang} and {Keze Wang}}, year = {2026}, eprint = {2610.05185v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.05185v1}, note = {First published: 2026-10-04; Recorded arXiv version: v1; Recorded version updated: 2026-10-04T12:49:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.05437", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.05437"}} @misc{arxiv_2610_05437, title = {{TeleTune: Evolving Agent Skills From Offline Telemetry}}, author = {{Justin Chih-Yao Chen} and {Elias Stengel-Eskin} and {Yan Chen} and {Pol Llado} and {Scott Counts} and {Mohit Bansal} and {Benjamin Van Durme} and {Harsh Jhamtani} and {Gaurav Verma}}, year = {2026}, eprint = {2610.05437v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.05437v2}, note = {First published: 2026-10-04; Recorded arXiv version: v2; Recorded version updated: 2026-10-06T03:17:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.05861", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.05861"}} @misc{arxiv_2610_05861, title = {{Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training}}, author = {{Yongxin Ning} and {Runliang Niu} and {Qianli Xing} and {Zhiyi Duan} and {Qingzu He} and {Pan Wang} and {Qi Wang}}, year = {2026}, eprint = {2610.05861v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.05861v1}, note = {First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T06:28:58Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.06829", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.06829"}} @misc{arxiv_2610_06829, title = {{CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling}}, author = {{Yifan Zhang} and {Yutong Dai} and {Viraj Prabhu} and {Zhiyuan Hu} and {Ran Xu} and {Zeyuan Chen}}, year = {2026}, eprint = {2610.06829v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.06829v1}, note = {First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T17:57:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.06898", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.06898"}} @misc{arxiv_2610_06898, title = {{DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections}}, author = {{Li Hu} and {Kanghua Mo} and {Yingbin Jin} and {Qingqing Ye} and {Haibo Hu}}, year = {2026}, eprint = {2610.06898v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.06898v1}, note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T03:03:00Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.07118", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.07118"}} @misc{arxiv_2610_07118, title = {{AMBER: Training Long-Horizon Web Agents through Append-Only Memory}}, author = {{Chinmay Savadikar} and {Zhaoyu Zhang} and {Mingyu Zhao} and {Shuang Xie} and {Han Li} and {Tianfu Wu} and {Lingyun Wang}}, year = {2026}, eprint = {2610.07118v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.07118v1}, note = {First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T17:11:07Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.07444", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.07444"}} @misc{arxiv_2610_07444, title = {{Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?}}, author = {{Aadi Chauhan} and {Arthur Ilyasov}}, year = {2026}, eprint = {2610.07444v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.07444v1}, note = {First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T21:50:50Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.07972", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.07972"}} @misc{arxiv_2610_07972, title = {{Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces}}, author = {{Yeji Park} and {Jaeyun Shim} and {Taesik Gong}}, year = {2026}, eprint = {2610.07972v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.07972v1}, note = {First published: 2026-10-06; Recorded arXiv version: v1; Recorded version updated: 2026-10-06T08:38:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.08773", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.08773"}} @misc{arxiv_2610_08773, title = {{AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model}}, author = {{Sarim Hashmi} and {Mukul Ranjan} and {Kshitij Mishra} and {Mikhail Kuznetsov} and {Praneeth Vepakomma} and {Nils Lukas}}, year = {2026}, eprint = {2610.08773v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.08773v1}, note = {First published: 2026-10-06; Recorded arXiv version: v1; Recorded version updated: 2026-10-06T17:56:43Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.09240", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.09240"}} @misc{arxiv_2610_09240, title = {{Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution}}, author = {{Wanjing Han} and {Levi Taiji Li} and {Mu Zhang} and {Yue Jiang} and {Guanhong Tao}}, year = {2026}, eprint = {2610.09240v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.09240v1}, note = {First published: 2026-10-07; Recorded arXiv version: v1; Recorded version updated: 2026-10-07T00:05:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.09469", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.09469"}} @misc{arxiv_2610_09469, title = {{Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents}}, author = {{Sarthak Choudhary} and {Mihai Christodorescu} and {Ashish Hooda} and {Somesh Jha} and {Tongxin Li} and {Damien Octeau}}, year = {2026}, eprint = {2610.09469v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.09469v1}, note = {First published: 2026-10-07; Recorded arXiv version: v1; Recorded version updated: 2026-10-07T05:24:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.09944", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.09944"}} @misc{arxiv_2610_09944, title = {{AgentTime: Can Agents Estimate and Control Their Own Runtime?}}, author = {{Michael Ofengenden} and {Maksym Andriushchenko}}, year = {2026}, eprint = {2610.09944v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.09944v2}, note = {First published: 2026-10-07; Recorded arXiv version: v2; Recorded version updated: 2026-10-08T09:06:36Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.11050", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.11050"}} @misc{arxiv_2610_11050, title = {{AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks}}, author = {{Xing Han Lù} and {Dheeraj Vattikonda} and {Sina Hajimiri} and {Fatemeh Pesaran Zadeh} and {Parishad BehnamGhader} and {Ghazwa Darwiche} and {Amirhossein Kazemnejad} and {Christopher Pal} and {Alexandre Drouin} and {Siva Reddy}}, year = {2026}, eprint = {2610.11050v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.11050v1}, note = {First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T01:03:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.11707", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.11707"}} @misc{arxiv_2610_11707, title = {{DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents}}, author = {{Yudong Bai} and {Yihong Chen} and {Quanming Yao} and {Yaqing Wang}}, year = {2026}, eprint = {2610.11707v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.11707v1}, note = {First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T11:12:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.11942", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.11942"}} @misc{arxiv_2610_11942, title = {{Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents}}, author = {{Jiaming Zhang} and {Xuan Wang} and {Fuyao Zhang} and {Yang Cao} and {Lingjuan Lyu} and {Wei Yang Bryan Lim}}, year = {2026}, eprint = {2610.11942v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.11942v1}, note = {First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T13:33:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.11963", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.11963"}} @misc{arxiv_2610_11963, title = {{Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes}}, author = {{Utku Boran Torun} and {Veli Karakaya} and {Eray Tüzün}}, year = {2026}, eprint = {2610.11963v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.11963v1}, note = {First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T13:44:53Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.12611", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.12611"}} @misc{arxiv_2610_12611, title = {{SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments}}, author = {{Tian Jin} and {Wenhao Wang} and {Jing Kang} and {Haoting Shi} and {Rui Ye} and {Yijun Lu} and {Siheng Chen}}, year = {2026}, eprint = {2610.12611v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.12611v2}, note = {First published: 2026-10-08; Recorded arXiv version: v2; Recorded version updated: 2026-10-14T08:40:10Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.12823", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.12823"}} @misc{arxiv_2610_12823, title = {{When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks}}, author = {{Yisheng Li} and {Dongming Han} and {Hongkun Pan} and {Bingcheng Mao} and {Zijian Wang} and {Yunlong Mao} and {Wei Tong} and {Sheng Zhong}}, year = {2026}, eprint = {2610.12823v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.12823v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T00:03:13Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.12866", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.12866"}} @misc{arxiv_2610_12866, title = {{CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving}}, author = {{Shangquan Sun} and {Ruoyu Chen} and {Zhirui Liu} and {Xiang Liu} and {Chenghao Qian} and {Wenqi Ren} and {Xiaochun Cao}}, year = {2026}, eprint = {2610.12866v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.12866v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T01:50:26Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.12984", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.12984"}} @misc{arxiv_2610_12984, title = {{Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction}}, author = {{Yuqi Huang} and {Hui Li} and {Yifei Cao} and {Zikun Cai} and {Tianci Xie} and {Yangfan Gao} and {Pinxue Guo} and {Chaoyun Zhang} and {Bingxuan Li} and {Rui Zheng} and {Hang Yan} and {Ning Liao}}, year = {2026}, eprint = {2610.12984v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.12984v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T04:32:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.13092", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.13092"}} @misc{arxiv_2610_13092, title = {{When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows}}, author = {{Yuchen Ling} and {Shengcheng Yu} and {Zhenyu Chen} and {Chunrong Fang}}, year = {2026}, eprint = {2610.13092v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.13092v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T06:45:23Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.13268", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.13268"}} @misc{arxiv_2610_13268, title = {{ConClick: Element-Wise Contrastive Learning Improves GUI Grounding}}, author = {{Ruotian Zhang} and {Yuhui Zhang} and {Junzhe Huang} and {Yu Xin} and {Hehe Fan} and {Xiaoxiao Sun}}, year = {2026}, eprint = {2610.13268v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.13268v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T09:20:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.13416", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.13416"}} @misc{arxiv_2610_13416, title = {{Web\$hell: A Unified Interface for Agentic Web Access}}, author = {{Sunghwan Kim} and {Deogyong Kim} and {Sangam Lee} and {Donguk Kwon} and {Dongha Lee}}, year = {2026}, eprint = {2610.13416v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.13416v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T11:23:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.13703", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.13703"}} @misc{arxiv_2610_13703, title = {{A Baseline Assessment for the Agentic Web Technology Stack}}, author = {{Vagner Figueredo de Santana} and {Diogo Cortiz}}, year = {2026}, eprint = {2610.13703v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.13703v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T14:59:24Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.14157", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.14157"}} @misc{arxiv_2610_14157, title = {{OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools}}, author = {{Chenyang Yan} and {Yingying Zhang} and {Kanzhi Cheng} and {Qiushi Sun} and {Zhengyuan Pan} and {Zheng Ma} and {Hang Yan} and {Yian Wang} and {Nuo Chen} and {Jialin Cao} and {Xingdong Gong} and {Wenpo Song} and {Han Chen} and {Zichen Ding} and {Fangzhi Xu} and {Shujian Huang} and {Xinyu Dai} and {Yichen Liu} and {Tiankuo Yao} and {Bo Wang} and {Ben Kao} and {Jianbing Zhang} and {Lewei Lu} and {Dahua Lin}}, year = {2026}, eprint = {2610.14157v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.14157v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T17:26:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.14228", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.14228"}} @misc{arxiv_2610_14228, title = {{Latent World Action Model for GUI Agents}}, author = {{Seungjun Yu} and {Hojun Choi} and {Seojeong Park} and {Jaeyo Shin} and {Hyunjung Shim}}, year = {2026}, eprint = {2610.14228v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.14228v1}, note = {First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T18:45:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.15138", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.15138"}} @misc{arxiv_2610_15138, title = {{The Agent Clicks Approve: Injected Page Text Makes Browser Agents Authorize Access the Task Never Named}}, author = {{Md Imran Hossen}}, year = {2026}, eprint = {2610.15138v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.15138v1}, note = {First published: 2026-10-10; Recorded arXiv version: v1; Recorded version updated: 2026-10-10T19:30:31Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.15502", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.15502"}} @misc{arxiv_2610_15502, title = {{From Observations to Authorized Actions: Measuring Source Information in Android Agents}}, author = {{Hyobin Ahn} and {Dongjae Lee}}, year = {2026}, eprint = {2610.15502v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.15502v1}, note = {First published: 2026-10-11; Recorded arXiv version: v1; Recorded version updated: 2026-10-11T10:09:44Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.15738", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.15738"}} @misc{arxiv_2610_15738, title = {{Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops}}, author = {{Jianlin Chen} and {Wenhui Chen} and {Chi Man Vong}}, year = {2026}, eprint = {2610.15738v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.15738v1}, note = {First published: 2026-10-11; Recorded arXiv version: v1; Recorded version updated: 2026-10-11T16:18:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.16234", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.16234"}} @misc{arxiv_2610_16234, title = {{Seg2Click: Learning Pixel-Level Action Masks for GUI Visual Grounding}}, author = {{Jingchao Wang} and {Dingjiang Huang}}, year = {2026}, eprint = {2610.16234v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.16234v1}, note = {First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T06:09:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.16319", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.16319"}} @misc{arxiv_2610_16319, title = {{HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks}}, author = {{Zijian Cai} and {Haowei Liu} and {Kailai Chen} and {Lin Peng} and {Cong Wan} and {Ziqi Zhang} and {Chunfeng Yuan} and {Bing Li} and {Weiming Hu} and {Haiyang Xu}}, year = {2026}, eprint = {2610.16319v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.16319v1}, note = {First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T07:42:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.16720", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.16720"}} @misc{arxiv_2610_16720, title = {{Learn from Move: the Next Step for GUI Agents}}, author = {{Jiahao Lu} and {Yize Shen} and {Chuanyuan Tan} and {Mianqiu Huang} and {Shicheng Fang} and {Xinchi Chen} and {Yining Zheng} and {Yuxin Wang} and {Xipeng Qiu}}, year = {2026}, eprint = {2610.16720v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.16720v1}, note = {First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T12:52:21Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.16778", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.16778"}} @misc{arxiv_2610_16778, title = {{PrivacyGuard: Source-Linked Sanitization and Locally Resolvable PII References for Cloud GUI Agents}}, author = {{Zian Yuan} and {Wei Li}}, year = {2026}, eprint = {2610.16778v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.16778v1}, note = {First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T13:34:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.17457", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.17457"}} @misc{arxiv_2610_17457, title = {{BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views}}, author = {{Yuetian Chen} and {Kaiyuan Zhang} and {Yuntao Du} and {Thomas Li} and {Mark Tenenholtz} and {Kyle Polley} and {Jerry Ma} and {Denis Yarats} and {Ninghui Li}}, year = {2026}, eprint = {2610.17457v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.17457v1}, note = {First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T22:17:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.17710", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.17710"}} @misc{arxiv_2610_17710, title = {{Adaptive-Group Process Rewards for GUI Agents}}, author = {{Zirui Shang} and {Yang Liu} and {Xin Shu} and {Zhi Gao} and {Xinxiao Wu} and {Lifeng Fan}}, year = {2026}, eprint = {2610.17710v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.17710v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T04:37:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.17792", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.17792"}} @misc{arxiv_2610_17792, title = {{MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search}}, author = {{Minghua Chen} and {Xingming Liao} and {Weiqiang Zhong} and {Zhuowei Wang}}, year = {2026}, eprint = {2610.17792v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.17792v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T06:20:38Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.17895", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.17895"}} @misc{arxiv_2610_17895, title = {{Interaction-as-a-Judge}}, author = {{Wayne Chi} and {I-Hung Hsu} and {Li Chen} and {Wei-Lin Chiang} and {Ion Stoica} and {Anastasios Nikolas Angelopoulos} and {Ameet Talwalkar} and {Chris Donahue} and {Cho-Jui Hsieh}}, year = {2026}, eprint = {2610.17895v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.17895v2}, note = {First published: 2026-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-10-14T06:37:47Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.17928", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.17928"}} @misc{arxiv_2610_17928, title = {{Learning How to Remember: Memory Modality Selection for GUI Agents}}, author = {{Taeyun Roh} and {Suhyeong Park} and {Gijin Kim} and {Wonjune Jang} and {Jaewoo Kang}}, year = {2026}, eprint = {2610.17928v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.17928v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T08:15:52Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.18067", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.18067"}} @misc{arxiv_2610_18067, title = {{WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution}}, author = {{Hang He} and {Linting Wang} and {Guanming Liu} and {Bo Mao} and {Jinxiu Liu} and {Yiran Suo} and {Maosen Zhou} and {Zhiheng Xi} and {Guanting Dong} and {Zhou Shao} and {Rui Zheng} and {Jie Zhou} and {Chengcheng Wan} and {Tao Gui} and {Qi Zhang} and {Xipeng Qiu} and {Xuanjing Huang}}, year = {2026}, eprint = {2610.18067v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.18067v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T09:52:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.18508", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.18508"}} @misc{arxiv_2610_18508, title = {{Towards Safe Autonomy for Computer Use}}, author = {{Dominik Seip} and {Bartol Markovinović} and {Matthias Hein}}, year = {2026}, eprint = {2610.18508v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.18508v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T15:03:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.18579", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.18579"}} @misc{arxiv_2610_18579, title = {{Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops}}, author = {{Yubo Li} and {Ramayya Krishnan} and {Rema Padman}}, year = {2026}, eprint = {2610.18579v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.18579v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T15:43:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.18784", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.18784"}} @misc{arxiv_2610_18784, title = {{Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents}}, author = {{Yuchen Lu} and {Julian McAuley} and {Lei Zhang}}, year = {2026}, eprint = {2610.18784v2}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.18784v2}, note = {First published: 2026-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-10-14T04:46:42Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.19100", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.19100"}} @misc{arxiv_2610_19100, title = {{GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning}}, author = {{Qingsong Xie} and {Jiahao Tian} and {Jiacheng Tang} and {Zhifeng Li} and {Madalina Ciobanu} and {Navan Preet Singh} and {Qingqing Mao} and {Ritankar Das}}, year = {2026}, eprint = {2610.19100v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.19100v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T19:37:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.19128", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.19128"}} @misc{arxiv_2610_19128, title = {{CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline}}, author = {{Yuxiang Lai} and {Jike Zhong} and {Chengzhi Liu} and {Ming Li} and {Haonan Wang} and {Xiaofeng Yang} and {Liang Zhao} and {Youbao Tang} and {Ruixi Fan}}, year = {2026}, eprint = {2610.19128v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.19128v1}, note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T20:01:18Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.19366", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.19366"}} @misc{arxiv_2610_19366, title = {{Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory}}, author = {{Minghao Guo} and {Qingyue Jiao} and {Xiujin Liu} and {Jianhong Pang} and {Ruimeng Yang} and {Naihao Xu} and {Liwei Che} and {Haochen Xue} and {Ziqi Wang} and {Xinying Cai} and {Jiaxuan Luo} and {Jiaxin Deng} and {Xuesong Ye} and {Jintao Qu} and {Wenyao Gao} and {Jingwen Gu} and {Chenyang Zhao} and {Shichun Liu} and {Guibin Zhang} and {Zefang Liu} and {Siyin Wang} and {Wujiang Xu} and {Danrui Li} and {Zeru Shi} and {Woongyeong Yeo} and {Shuang Liu} and {Wei-Chieh Huang} and {Weizhi Zhang} and {Tianyu Yang} and {Kangsan Kim} and {Yebowen Hu} and {Bowen Wen} and {Bowen Jiang} and {Haohao Su} and {Ming Yin} and {Sheldon Yu} and {Mian Zhang} and {Yuyan Chen} and {Hanrong Zhang} and {Kai Mei} and {Zihao Zhang} and {Mingyu Jin} and {Xi Zhu} and {Hengyi Wang} and {Tianxin Wei} and {Linyong Nan} and {Zhenwen Liang} and {Zhendong Chu} and {Ziqi Huang} and {Yongye Su} and {Sixun Dong} and {Shujian Liu} and {Kaiqu Liang} and {Jiaojiao Han} and {Zhaoye Fei} and {Kun Wang} and {Shihan Dou} and {Zhichun Guo} and {Xingjian Diao} and {Zeqi Gu} and {Heng Wang} and {Tao Feng} and {Cheng Qian} and {Hamid Palangi} and {Silei Xu} and {Xi Yun} and {Yi Zhu} and {Shilong Liu} and {Qingsong Wen} and {Sung Ju Hwang} and {Zuxuan Wu} and {Yu-Gang Jiang} and {Yiyu Shi} and {Dimitris N. Metaxas} and {Jiaxuan You} and {Julian McAuley} and {Mengdi Wang} and {Jiawei Han} and {Philip S. Yu} and {Ziyi Ye}}, year = {2026}, eprint = {2610.19366v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.19366v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T01:11:57Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.19384", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.19384"}} @misc{arxiv_2610_19384, title = {{MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation}}, author = {{Yuke Wang} and {Benlei Cui} and {Shen Pang} and {Xuemei Dong} and {Longtao Huang} and {Hui Xue} and {Yuwen Zhai} and {Junjie Li} and {Jingqun Tang} and {Haiwen Hong}}, year = {2026}, eprint = {2610.19384v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.19384v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T01:30:03Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.19834", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.19834"}} @misc{arxiv_2610_19834, title = {{Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents}}, author = {{Md Farhan Ishmam} and {Kenneth Marino}}, year = {2026}, eprint = {2610.19834v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.19834v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T09:06:49Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.19900", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.19900"}} @misc{arxiv_2610_19900, title = {{How GUI Agents Fail: GraceBench for Execution Stability Diagnosis}}, author = {{Ridong Zhang} and {Shuxian Liang} and {Chaoqun Wan} and {Zhen Huang} and {Xian-Sheng Hua}}, year = {2026}, eprint = {2610.19900v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.19900v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T09:58:40Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.20100", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.20100"}} @misc{arxiv_2610_20100, title = {{Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution}}, author = {{Wenkui Yang} and {Yiming Hao} and {Kai Zhou} and {Chengyu Pu} and {Yuzhe Zhang} and {Jie Cao} and {Jin Huang} and {Shuai Ma} and {Feng Tian}}, year = {2026}, eprint = {2610.20100v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.20100v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T12:35:59Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.20107", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.20107"}} @misc{arxiv_2610_20107, title = {{Why Generate a Click? Plug-in Decision Heads for Web Agents}}, author = {{Chengguang Gan} and {Yunhao Liang} and {Hanjun Wei} and {Qinghao Zhang} and {Zhixi Cai} and {Shiwen Ni}}, year = {2026}, eprint = {2610.20107v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.20107v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T12:39:51Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.20390", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.20390"}} @misc{arxiv_2610_20390, title = {{STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents}}, author = {{Shuo Wang} and {Sifan Zhou} and {Xiaobo Wang} and {Tianyu Fu} and {Chenxu Zhao} and {Anyang Su} and {Hanning Wang} and {Ping Jiang} and {Minghui Wu}}, year = {2026}, eprint = {2610.20390v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.20390v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T15:53:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.20584", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.20584"}} @misc{arxiv_2610_20584, title = {{Player-1: Learning to Play from Synthetic Experience}}, author = {{Mingyu Ouyang} and {Yiran Wang} and {Siyuan Hu} and {Xingyilang Yin} and {Huiqiang Sun} and {Guangzhi Wang} and {Junfu Pu} and {Cheng Cheng} and {Honghao Chen} and {Ying Shan} and {Mike Zheng Shou} and {Hwee Tou Ng}}, year = {2026}, eprint = {2610.20584v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.20584v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T17:57:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.20939", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.20939"}} @misc{arxiv_2610_20939, title = {{MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments}}, author = {{Panrong Tong} and {Quyu Kong} and {Pengxiang Li} and {Tianyu Xia} and {Hanzhang Zhou} and {Lei Wang} and {Chenglin Cai} and {Long Li} and {Long Chen} and {Jianan Zhang} and {Zhengwen Zeng} and {Xu Zhang} and {Gongjie Zhang} and {Yue Wang} and {Steven Hoi}}, year = {2026}, eprint = {2610.20939v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.20939v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T21:06:01Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22200", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22200"}} @misc{arxiv_2610_22200, title = {{OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use}}, author = {{Hanzhang Zhou} and {Long Li} and {Quyu Kong} and {Lei Wang} and {Panrong Tong} and {Long Chen} and {Tianyu Xia} and {Gongjie Zhang} and {Xu Zhang} and {Chen Liu} and {Jianan Zhang} and {Chenglin Cai} and {Zhengwen Zeng} and {Steven Hoi} and {Yue Wang}}, year = {2026}, eprint = {2610.22200v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22200v1}, note = {First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T16:51:35Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22234", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22234"}} @misc{arxiv_2610_22234, title = {{OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents}}, author = {{Bowen Yang} and {Kaiming Jin} and {Zichen Ding} and {Zhenyu Wu} and {Zehao Li} and {Zhoumianze Liu} and {Kanzhi Cheng} and {Fangzhi Xu} and {Yanan Sun} and {Qiushi Sun} and {Yu Qiao}}, year = {2026}, eprint = {2610.22234v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22234v1}, note = {First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T17:14:02Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22280", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22280"}} @misc{arxiv_2610_22280, title = {{LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents}}, author = {{Qingni Wang} and {Changdae Oh} and {Yuzhe Yang} and {Sharon Li} and {Jiachen Yang} and {Ang Li} and {Xin Eric Wang}}, year = {2026}, eprint = {2610.22280v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22280v1}, note = {First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T17:40:12Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22408", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22408"}} @misc{arxiv_2610_22408, title = {{ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation}}, author = {{Tengda Guo} and {Jiawang Hu} and {Yifei Tao} and {Yin Wang} and {Haotian Hu} and {Fanyi Wang} and {Liujuan Tang}}, year = {2026}, eprint = {2610.22408v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22408v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T14:39:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22539", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22539"}} @misc{arxiv_2610_22539, title = {{Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks}}, author = {{Md Farhan Ishmam} and {Minh Pham Dinh} and {Kenneth Marino}}, year = {2026}, eprint = {2610.22539v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22539v1}, note = {First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T18:37:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22672", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22672"}} @misc{arxiv_2610_22672, title = {{Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation}}, author = {{Adamo Orsini} and {Seyed Mehdi Ayyoubzadeh} and {Sadman Rakib Pinon} and {Hannuo Zhang} and {Koosha Gholipour Baradari} and {Yuanhao Yu} and {Xinxin Zuo} and {Yang Wang}}, year = {2026}, eprint = {2610.22672v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22672v1}, note = {First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T21:40:34Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22697", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22697"}} @misc{arxiv_2610_22697, title = {{What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics}}, author = {{Umar Iqbal}}, year = {2026}, eprint = {2610.22697v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22697v1}, note = {First published: 2026-10-15; Recorded arXiv version: v1; Recorded version updated: 2026-10-15T22:02:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.22990", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.22990"}} @misc{arxiv_2610_22990, title = {{PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas}}, author = {{Haoming Li} and {Defu Cao} and {Xu Hu} and {Yingtao Luo} and {Yiyang Wang} and {Xianghe Xu} and {Jiashu He} and {Wanting Jiang} and {Yifan Zhang} and {Yunhan Zhao} and {Siyang Wu} and {Chen Yang} and {Haixin Wang} and {Zheyuan Deng} and {Taoran Li} and {Jingwen Zhang} and {Zhejian Peng} and {Shushu Liang} and {Yue Zhao} and {Bingzhe Li} and {Feng Chen} and {Yifan Wang} and {Jintao Huang} and {Yijun Wang} and {Yuexing Hao} and {Xiaomin Li}}, year = {2026}, eprint = {2610.22990v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.22990v1}, note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T06:14:55Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.23012", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.23012"}} @misc{arxiv_2610_23012, title = {{Adaptation of Computer Use Agents to New Software with User Manuals}}, author = {{Chulhoon Yoon} and {Kyungri Park} and {Jinyeong Yun} and {Daeyun Jeong} and {Sukmin Yun} and {Woohwan Jung}}, year = {2026}, eprint = {2610.23012v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.23012v1}, note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T06:44:56Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.23303", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.23303"}} @misc{arxiv_2610_23303, title = {{MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents}}, author = {{Songping Wang} and {Borui Li} and {Qinglong Liu} and {Yueming Lyu} and {Yi Huang} and {Fengting Li} and {Chao Feng} and {Caifeng Shan}}, year = {2026}, eprint = {2610.23303v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.23303v1}, note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T11:06:37Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.23307", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.23307"}} @misc{arxiv_2610_23307, title = {{MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection}}, author = {{Songping Wang} and {Peiyang Li} and {Yi Huang} and {Fengting Li} and {Xuhao Ran} and {Yueming Lyu} and {Chao Feng} and {Caifeng Shan}}, year = {2026}, eprint = {2610.23307v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.23307v1}, note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T11:10:30Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.23986", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2610.23986"}} @misc{arxiv_2610_23986, title = {{BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References}}, author = {{Xinyu Fang} and {Yuchi Wang} and {Weihao Yu} and {Rongyao Fang} and {Zhaohai Li} and {Zhixun Li} and {Tiancheng Gu} and {Xilin Wei} and {Yuhang Zang} and {Hongsheng Li} and {Dahua Lin} and {Guofeng Zhang} and {Shuai Bai} and {Zhibo Yang} and {Dayiheng Liu}}, year = {2026}, eprint = {2610.23986v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.23986v1}, note = {First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T12:46:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.24277", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.24277"}} @misc{arxiv_2610_24277, title = {{SPIDES: Information-Flow Control for Browser Agents}}, author = {{Egor Zverev} and {Juhee Kim} and {Leon Trampert} and {Boris Köpf} and {Aashish Kolluri} and {Shruti Tople} and {Santiago Zanella-Béguelin}}, year = {2026}, eprint = {2610.24277v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.24277v1}, note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T22:12:45Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.24372", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.24372"}} @misc{arxiv_2610_24372, title = {{Beyond Next-Screen Prediction: The Decision Value of GUI World Models}}, author = {{Sizhe Tang} and {Hanhan Zhou} and {Jeffrey Svajlenko} and {Rashmi Gangadharaiah}}, year = {2026}, eprint = {2610.24372v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.24372v1}, note = {First published: 2026-10-17; Recorded arXiv version: v1; Recorded version updated: 2026-10-17T02:03:20Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26071", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26071"}} @misc{arxiv_2610_26071, title = {{CUA-Lite: An Open Platform for Computer Use Agents}}, author = {{Zhanhui Zhou} and {Weichen Zhang} and {Haoran Liu} and {Lingjie Chen} and {Tianneng Shi} and {Kevin Lin} and {Zhengyuan Yang} and {Lijuan Wang} and {Dawn Song}}, year = {2026}, eprint = {2610.26071v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26071v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T09:30:54Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26203", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26203"}} @misc{arxiv_2610_26203, title = {{Focused Omni-Modal GUI Agents}}, author = {{Fuyao Zhang} and {Wenwen He} and {Jiaming Zhang} and {Yurong Hao} and {Xuan Wang} and {Guowei Guan} and {Che Wang} and {Longtao Huang} and {Wei Yang Bryan Lim}}, year = {2026}, eprint = {2610.26203v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26203v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T11:30:48Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26469", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26469"}} @misc{arxiv_2610_26469, title = {{VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards}}, author = {{Zhizhou Wang} and {Yaxi Lu} and {Zhong Zhang} and {Zikun Hu} and {Xin Cong} and {Yankai Lin} and {Fangming Liu}}, year = {2026}, eprint = {2610.26469v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26469v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T14:17:33Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26503", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26503"}} @misc{arxiv_2610_26503, title = {{ScopeMem: Latent Memory That Learns Where to Revise Frozen GUI Agents}}, author = {{Zhicheng Zheng} and {Cheng Zhang} and {Shengping Yu} and {Tianxiang Zhao}}, year = {2026}, eprint = {2610.26503v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26503v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T14:38:41Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26660", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26660"}} @misc{arxiv_2610_26660, title = {{Tandem: Serving Hybrid Linear-Attention GUI Agents on Mobile NPUs}}, author = {{Zhuomin Chen} and {Jingchao Ni} and {Xu Zheng} and {Yong Chen} and {Mo Sha} and {Wei Cheng} and {Dongsheng Luo}}, year = {2026}, eprint = {2610.26660v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26660v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T16:18:16Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26703", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26703"}} @misc{arxiv_2610_26703, title = {{Comparing Computer Use Behavior Across Multiple Levels of Abstraction}}, author = {{Ananya Gubbi Mohanbabu} and {Rosiana Natalie} and {Anhong Guo} and {Amy Pavel}}, year = {2026}, eprint = {2610.26703v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26703v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T16:39:11Z.} } % AwesomeCUA: {"catalog_id": "arxiv:2610.26828", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26828"}} @misc{arxiv_2610_26828, title = {{Agent World Model in the Wild: Computer-Use Agent Environment Synthesis}}, author = {{Zhaoyang Wang} and {Qianhui Wu} and {Haorui Wang} and {Simon Yu} and {Baolin Peng} and {Canwen Xu} and {Hao Cheng} and {Wenlin Yao} and {Boyi Liu} and {Yite Wang} and {Jianfeng Gao} and {Huaxiu Yao}}, year = {2026}, eprint = {2610.26828v1}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2610.26828v1}, note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T17:55:35Z.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/2983990.2984020", "catalog_id": "url:347925d0f440d6396080", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/2983990.2984020"}, "publication": {"authors": ["Shaon Barman", "Sarah Chasins", "Ras Bodik", "Sumit Gulwani"], "date_basis": "Supplied month precision: 2016-11. year=2016, month=November", "date_parts": [2016, 11], "doi": "10.1145/2983990.2984020", "event_dates": null, "evidence_urls": ["https://www.microsoft.com/en-us/research/publication/ringer-web-automation-demonstration/bibtex/", "https://2016.splashcon.org/track/splash-2016-oopsla", "https://www.microsoft.com/en-us/research/publication/ringer-web-automation-demonstration/", "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/12/oopsla16-web.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The original manuscript and MSR BibTeX print Sarah Chasins and Ras Bodik. The official conference profiles expand these to Sarah E. Chasins and Rastislav Bod\u00edk; the printed publication names are preserved. Page range, volume and exact publication day are not established by the retained citation sources.", "pages": null, "pdf_url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/12/oopsla16-web.pdf", "publisher": null, "series": null, "title": "Ringer: Web Automation by Demonstration", "type": "conference-paper", "url": "https://doi.org/10.1145/2983990.2984020", "venue": "OOPSLA 2016", "volume": null}} @inproceedings{cua_07942b5af1a8c0ffa9c7322a, title = {{Ringer: Web Automation by Demonstration}}, author = {{Shaon Barman} and {Sarah Chasins} and {Ras Bodik} and {Sumit Gulwani}}, year = {2016}, month = nov, booktitle = {OOPSLA 2016}, doi = {10.1145/2983990.2984020}, url = {https://doi.org/10.1145/2983990.2984020}, note = {Publication date: 2016-11.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/3025453.3025483", "catalog_id": "url:392a602c660ffa91be46", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/3025453.3025483"}, "publication": {"authors": ["Toby Jia-Jun Li", "Amos Azaria", "Brad A. Myers"], "date_basis": "Supplied year precision: 2017. Publications: SUGILITE, CHI 2017 Only publication year is asserted; event dates are kept separate.", "date_parts": [2017], "doi": "10.1145/3025453.3025483", "event_dates": null, "evidence_urls": ["https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Related to later APPINITE and PUMICE work but distinguished here by its 2017 three-author publication and base demonstration-automation contribution. Publication month/day are not independently identified by the retained sources.", "pages": "6038-6049", "pdf_url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf", "publisher": null, "series": null, "title": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "type": "conference-paper", "url": "https://doi.org/10.1145/3025453.3025483", "venue": "Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems", "volume": null}} @inproceedings{cua_6b7f9d608ed89d1625610eb1, title = {{SUGILITE: Creating Multimodal Smartphone Automation by Demonstration}}, author = {{Toby Jia-Jun Li} and {Amos Azaria} and {Brad A. Myers}}, year = {2017}, booktitle = {Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems}, pages = {6038-6049}, doi = {10.1145/3025453.3025483}, url = {https://doi.org/10.1145/3025453.3025483}, note = {Publication date: 2017.} } % AwesomeCUA: {"canonical_source_url": "https://proceedings.mlr.press/v70/shi17a.html", "catalog_id": "url:52a3261eb6a19b402e88", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {}, "publication": {"authors": ["Tianlin Shi", "Andrej Karpathy", "Linxi Fan", "Jonathan Hernandez", "Percy Liang"], "date_basis": "Publisher citation_publication_date metadata explicitly states 2017/07/17; this is separate from the conference interval.", "date_parts": [2017, 7, 17], "doi": null, "event_dates": "06--11 Aug (conference interval reported in the publisher BibTeX month field)", "evidence_urls": ["https://proceedings.mlr.press/v70/shi17a.html", "https://proceedings.mlr.press/v70/shi17a/shi17a.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Publisher citation uses Tianlin Shi and Linxi Fan; the PDF also prints the nicknames Tim and Jim. The ordered publisher author names are retained. DOI not supplied in the retained publisher citation. Publisher metadata supplies the publication date separately from the conference interval.", "pages": "3135-3144", "pdf_url": "https://proceedings.mlr.press/v70/shi17a/shi17a.pdf", "publisher": "PMLR", "series": "Proceedings of Machine Learning Research", "title": "World of Bits: An Open-Domain Platform for Web-Based Agents", "type": "conference-paper", "url": "https://proceedings.mlr.press/v70/shi17a.html", "venue": "Proceedings of the 34th International Conference on Machine Learning", "volume": "70"}} @inproceedings{cua_ba263493b78b0263c7933138, title = {{World of Bits: An Open-Domain Platform for Web-Based Agents}}, author = {{Tianlin Shi} and {Andrej Karpathy} and {Linxi Fan} and {Jonathan Hernandez} and {Percy Liang}}, year = {2017}, month = jul, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, publisher = {PMLR}, series = {Proceedings of Machine Learning Research}, volume = {70}, pages = {3135-3144}, url = {https://proceedings.mlr.press/v70/shi17a.html}, note = {Publication date: 2017-07-17.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/1753326.1753555", "catalog_id": "url:6262c757080f8838e62c", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/1753326.1753555"}, "publication": {"authors": ["Tsung-Hsiang Chang", "Tom Yeh", "Robert C. Miller"], "date_basis": "Supplied month precision: 2010-04. Date Issued: April 2010", "date_parts": [2010, 4], "doi": "10.1145/1753326.1753555", "event_dates": null, "evidence_urls": ["https://dspace.mit.edu/entities/publication/6a6097ba-1d97-43cf-bc70-04b5af02efd5"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Distinct visual-testing contribution from the 2009 Sikuli paper. The institutional abstract and published-version citation supply the retained evidence. Exact publication day and operating-system coverage are not established in the accessible institutional abstract.", "pages": "1535-1544", "pdf_url": null, "publisher": null, "series": null, "title": "GUI Testing Using Computer Vision", "type": "conference-paper", "url": "https://doi.org/10.1145/1753326.1753555", "venue": "Proceedings of the 28th International Conference on Human Factors in Computing Systems (CHI '10)", "volume": null}} @inproceedings{cua_08a6c6d3e0e8b509ecb90301, title = {{GUI Testing Using Computer Vision}}, author = {{Tsung-Hsiang Chang} and {Tom Yeh} and {Robert C. Miller}}, year = {2010}, month = apr, booktitle = {Proceedings of the 28th International Conference on Human Factors in Computing Systems (CHI '10)}, pages = {1535-1544}, doi = {10.1145/1753326.1753555}, url = {https://doi.org/10.1145/1753326.1753555}, note = {Publication date: 2010-04.} } % AwesomeCUA: {"canonical_source_url": "https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "catalog_id": "url:628b5251757bb3888e89", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {}, "publication": {"authors": ["James Allen", "Nathanael Chambers", "George Ferguson", "Lucian Galescu", "Hyuckchul Jung", "Mary Swift", "William Taysom"], "date_basis": "Supplied year precision: 2007. Papers section: AAAI-2007", "date_parts": [2007], "doi": null, "event_dates": null, "evidence_urls": ["https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "https://www.cs.rochester.edu/research/cisd/projects/plow/"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The ordered names follow the original published paper, without expanding initials or replacing names from secondary indexes. DOI and volume number are not supplied in the retained primary sources. No exact publication month/day is established.", "pages": "1514-1519", "pdf_url": "https://cdn.aaai.org/AAAI/2007/AAAI07-240.pdf", "publisher": null, "series": null, "title": "PLOW: A Collaborative Task Learning Agent", "type": "conference-paper", "url": "https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf", "venue": "Twenty-Second AAAI National Conference on Artificial Intelligence", "volume": null}} @inproceedings{cua_4e2f12a215bd1cadd864f498, title = {{PLOW: A Collaborative Task Learning Agent}}, author = {{James Allen} and {Nathanael Chambers} and {George Ferguson} and {Lucian Galescu} and {Hyuckchul Jung} and {Mary Swift} and {William Taysom}}, year = {2007}, booktitle = {Twenty-Second AAAI National Conference on Artificial Intelligence}, pages = {1514-1519}, url = {https://aaai.org/Papers/AAAI/2007/AAAI07-240.pdf}, note = {Publication date: 2007.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/3210240.3210339", "catalog_id": "url:901ca855640457dfe2f1", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/3210240.3210339"}, "publication": {"authors": ["Toby Jia-Jun Li", "Oriana Riva"], "date_basis": "Supplied month precision: 2018-06. Publication line: MobiSys 2018, June 2018", "date_parts": [2018, 6], "doi": "10.1145/3210240.3210339", "event_dates": null, "evidence_urls": ["https://www.microsoft.com/en-us/research/publication/kite-building-conversational-bots-mobile-apps/", "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Final proceedings page range and volume are not established in the retained first-party citation. The paper states a 14-page extent, not a page range. Exact publication day is unknown.", "pages": null, "pdf_url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2018/05/kite_mobisys18.pdf", "publisher": null, "series": null, "title": "Kite: Building Conversational Bots from Mobile Apps", "type": "conference-paper", "url": "https://doi.org/10.1145/3210240.3210339", "venue": "The 16th Annual International Conference on Mobile Systems, Applications, and Services", "volume": null}} @inproceedings{cua_93605b13ec414a1e08029b6d, title = {{Kite: Building Conversational Bots from Mobile Apps}}, author = {{Toby Jia-Jun Li} and {Oriana Riva}}, year = {2018}, month = jun, booktitle = {The 16th Annual International Conference on Mobile Systems, Applications, and Services}, doi = {10.1145/3210240.3210339}, url = {https://doi.org/10.1145/3210240.3210339}, note = {Publication date: 2018-06.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/3242587.3242661", "catalog_id": "url:97c0b1896525632434e2", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/3242587.3242661"}, "publication": {"authors": ["Sarah E. Chasins", "Maria Mueller", "Rastislav Bodik"], "date_basis": "Supplied year precision: 2018. Rousillon entry: UIST 2018", "date_parts": [2018], "doi": "10.1145/3242587.3242661", "event_dates": null, "evidence_urls": ["https://schasins.com/papers/", "https://schasins.com/assets/papers/rousillon.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "This is browser interaction learned from demonstrations, rather than a generic server-side crawling library. Final proceedings page range and volume are not established. Manuscript pages 1-13 are not substituted for publisher pagination. Exact publication month/day is not inferred from conference dates.", "pages": null, "pdf_url": "https://schasins.com/assets/papers/rousillon.pdf", "publisher": null, "series": null, "title": "Rousillon: Scraping Distributed Hierarchical Web Data", "type": "conference-paper", "url": "https://doi.org/10.1145/3242587.3242661", "venue": "Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology", "volume": null}} @inproceedings{cua_b85f11762562177944b6898f, title = {{Rousillon: Scraping Distributed Hierarchical Web Data}}, author = {{Sarah E. Chasins} and {Maria Mueller} and {Rastislav Bodik}}, year = {2018}, booktitle = {Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology}, doi = {10.1145/3242587.3242661}, url = {https://doi.org/10.1145/3242587.3242661}, note = {Publication date: 2018.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/1622176.1622213", "catalog_id": "url:a4cdb2ee0d07d3980651", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/1622176.1622213"}, "publication": {"authors": ["Tom Yeh", "Tsung-Hsiang Chang", "Robert C. Miller"], "date_basis": "Supplied month precision: 2009-10. Date Issued: October 2009", "date_parts": [2009, 10], "doi": "10.1145/1622176.1622213", "event_dates": null, "evidence_urls": ["https://dspace.mit.edu/entities/publication/604a3f79-451d-4186-a94e-d12690ffe40a"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Institutional abstract and published-version citation supply the retained evidence; the institution identifies an author final manuscript record. Exact publication day is not supplied. Operating-system-specific experiments are not asserted.", "pages": "183-192", "pdf_url": null, "publisher": null, "series": null, "title": "Sikuli: Using GUI screenshots for search and automation", "type": "conference-paper", "url": "https://doi.org/10.1145/1622176.1622213", "venue": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)", "volume": null}} @inproceedings{cua_510831381c08385eb74fb95e, title = {{Sikuli: Using GUI screenshots for search and automation}}, author = {{Tom Yeh} and {Tsung-Hsiang Chang} and {Robert C. Miller}}, year = {2009}, month = oct, booktitle = {Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)}, pages = {183-192}, doi = {10.1145/1622176.1622213}, url = {https://doi.org/10.1145/1622176.1622213}, note = {Publication date: 2009-10.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/3126594.3126651", "catalog_id": "url:b560b5d6abaab98483f6", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/3126594.3126651"}, "publication": {"authors": ["Biplab Deka", "Zifeng Huang", "Chad Franzen", "Joshua Hibschman", "Daniel Afergan", "Yang Li", "Jeffrey Nichols", "Ranjitha Kumar"], "date_basis": "Supplied day precision: 2017-10-20. PDF cover, Published: 20 October 2017 The 18 January 2026 download date and October 22-25 conference dates are not publication dates.", "date_parts": [2017, 10, 20], "doi": "10.1145/3126594.3126651", "event_dates": null, "evidence_urls": ["https://danafergan.com/publications/deka2017rico.pdf", "https://dev.interactionmining.org/archive/rico"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The paper is a distinct resource from the already cataloged Rico dataset (url:0b134b082a7bd507fc6a). The publisher PDF describes 9.7k apps and 72k screens; the project page describes 9.3k apps and 66k screens. The annotation intentionally supplies no merged size claim. No volume number is supplied for this proceedings article.", "pages": "845-854", "pdf_url": "https://danafergan.com/publications/deka2017rico.pdf", "publisher": null, "series": null, "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications", "type": "conference-paper", "url": "https://doi.org/10.1145/3126594.3126651", "venue": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology", "volume": null}} @inproceedings{cua_402ed654426712089390317c, title = {{Rico: A Mobile App Dataset for Building Data-Driven Design Applications}}, author = {{Biplab Deka} and {Zifeng Huang} and {Chad Franzen} and {Joshua Hibschman} and {Daniel Afergan} and {Yang Li} and {Jeffrey Nichols} and {Ranjitha Kumar}}, year = {2017}, month = oct, booktitle = {UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology}, pages = {845-854}, doi = {10.1145/3126594.3126651}, url = {https://doi.org/10.1145/3126594.3126651}, note = {Publication date: 2017-10-20.} } % AwesomeCUA: {"canonical_source_url": "https://ieeexplore.ieee.org/document/8506506", "catalog_id": "url:ba2c664c1b3c6f1b172f", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {}, "publication": {"authors": ["Toby Jia-Jun Li", "Igor Labutov", "Xiaohan Nancy Li", "Xiaoyi Zhang", "Wenze Shi", "Wanling Ding", "Tom M. Mitchell", "Brad A. Myers"], "date_basis": "Supplied year precision: 2018. APPINITE publication citation: VL/HCC 2018", "date_parts": [2018], "doi": null, "event_dates": null, "evidence_urls": ["https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf", "https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/publications/"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The base SUGILITE framework and later PUMICE work are distinct publications; this paper focuses on resolving data-description ambiguity in demonstrations. Author-hosted manuscript and institutional publication lists supply the retained evidence. DOI, final page range, and exact publication day remain unknown.", "pages": null, "pdf_url": "https://toby.li/files/TobyLi-VLHCC18-APPINITE.pdf", "publisher": null, "series": null, "title": "APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions", "type": "conference-paper", "url": "https://ieeexplore.ieee.org/document/8506506", "venue": "Proceedings of the 2018 IEEE Symposium on Visual Languages and Human-Centric Computing", "volume": null}} @inproceedings{cua_753e73012e6a2483f242138b, title = {{APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions}}, author = {{Toby Jia-Jun Li} and {Igor Labutov} and {Xiaohan Nancy Li} and {Xiaoyi Zhang} and {Wenze Shi} and {Wanling Ding} and {Tom M. Mitchell} and {Brad A. Myers}}, year = {2018}, booktitle = {Proceedings of the 2018 IEEE Symposium on Visual Languages and Human-Centric Computing}, url = {https://ieeexplore.ieee.org/document/8506506}, note = {Publication date: 2018.} } % AwesomeCUA: {"canonical_source_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "catalog_id": "url:beb8f1fd6b945ffc9d93", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {}, "publication": {"authors": ["Fei Tang", "Zhangxuan Gu", "Zhengxi Lu", "Shangzhan Zhang", "Zhengwen Zeng", "Shuheng Shen", "Changhua Meng", "Yuchen Yan", "Wenqi Zhang", "Yongliang Shen", "Weiming Lu", "Yueting Zhuang"], "date_basis": "Explicit publisher metadata: month = {June}, year = {2026}; precision=month.", "date_parts": [2026, 6], "doi": null, "event_dates": null, "evidence_urls": ["https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "https://openaccess.thecvf.com/content/CVPR2026/papers/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.pdf"], "identity_basis": "No title/DOI/canonical URL match in the current paper catalog or raw archive; closest substantive same-team works were reread and have different contributions.", "issue": null, "notes": "CVF open-access accepted version; PDF states that the final proceedings version is on IEEE Xplore.", "pages": "13007-13016", "pdf_url": "https://openaccess.thecvf.com/content/CVPR2026/papers/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.pdf", "publisher": null, "series": null, "title": "GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning", "type": "conference-paper", "url": "https://openaccess.thecvf.com/content/CVPR2026/html/Tang_GUI-SAGE_Enhancing_GUI_Automation_with_Self-Explanatory_Learning_CVPR_2026_paper.html", "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "volume": null}} @inproceedings{cua_a6fbf231c6d3a11f67403503, title = {{GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning}}, author = {{Fei Tang} and {Zhangxuan Gu} and {Zhengxi Lu} and {Shangzhan Zhang} and {Zhengwen Zeng} and {Shuheng Shen} and {Changhua Meng} and {Yuchen Yan} and {Wenqi Zhang} and {Yongliang Shen} and {Weiming Lu} and {Yueting Zhuang}}, year = {2026}, month = jun, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, pages = {13007-13016}, url = {https://openaccess.thecvf.com/content/CVPR2026/html/Tang\_GUI-SAGE\_Enhancing\_GUI\_Automation\_with\_Self-Explanatory\_Learning\_CVPR\_2026\_paper.html}, note = {Publication date: 2026-06.} } % AwesomeCUA: {"canonical_source_url": "https://acypher.com/Publications/CHI91/EagerCHI.html", "catalog_id": "url:bf0c11018e49dff6aeec", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {}, "publication": {"authors": ["Allen Cypher"], "date_basis": "Supplied year precision: 1991. Opening CHI 1991 citation and copyright", "date_parts": [1991], "doi": null, "event_dates": null, "evidence_urls": ["https://acypher.com/Eager/", "https://acypher.com/Publications/CHI91/EagerCHI.html"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "The 1991 conference paper is kept distinct from the 1991 video and 1993/1995 reprints listed on the author project page. Macintosh/HyperCard is tagged desktop; it is not represented as support for contemporary macOS. DOI not verified in a retained first-party source. Exact publication month/day is not inferred from conference dates.", "pages": "33-39", "pdf_url": null, "publisher": null, "series": null, "title": "Eager: Programming Repetitive Tasks by Example", "type": "conference-paper", "url": "https://acypher.com/Publications/CHI91/EagerCHI.html", "venue": "Proceedings of CHI '91", "volume": null}} @inproceedings{cua_79e3af204750d438f5d43781, title = {{Eager: Programming Repetitive Tasks by Example}}, author = {{Allen Cypher}}, year = {1991}, booktitle = {Proceedings of CHI '91}, pages = {33-39}, url = {https://acypher.com/Publications/CHI91/EagerCHI.html}, note = {Publication date: 1991.} } % AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/1240624.1240767", "catalog_id": "url:cccd967aa993404d74d0", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/1240624.1240767"}, "publication": {"authors": ["Greg Little", "Tessa A. Lau", "Allen Cypher", "James Lin", "Eben M. Haber", "Eser Kandogan"], "date_basis": "Supplied year precision: 2007. CHI 2007 proceedings heading and copyright year The IBM page has an unlabeled Date of 22 Oct 2007, while the paper gives April/May event dates. Their roles do not establish a reliable day-level publication date.", "date_parts": [2007], "doi": "10.1145/1240624.1240767", "event_dates": null, "evidence_urls": ["https://research.ibm.com/publications/koala-capture-share-automate-personalize-business-processes-on-the-web", "https://plunk.org/eben/PublishedPapers/KoalaCHI.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "This proposal is the specific Koala paper. It does not automatically merge every later CoScripter publication or project record. Exact publication date is unresolved; only the clearly established year is proposed.", "pages": "943-946", "pdf_url": "https://plunk.org/eben/PublishedPapers/KoalaCHI.pdf", "publisher": null, "series": null, "title": "Koala: Capture, Share, Automate, Personalize Business Processes on the Web", "type": "conference-paper", "url": "https://doi.org/10.1145/1240624.1240767", "venue": "CHI 2007 Proceedings", "volume": null}} @inproceedings{cua_1b4a3a269ca9f1884a566476, title = {{Koala: Capture, Share, Automate, Personalize Business Processes on the Web}}, author = {{Greg Little} and {Tessa A. Lau} and {Allen Cypher} and {James Lin} and {Eben M. Haber} and {Eser Kandogan}}, year = {2007}, booktitle = {CHI 2007 Proceedings}, pages = {943-946}, doi = {10.1145/1240624.1240767}, url = {https://doi.org/10.1145/1240624.1240767}, note = {Publication date: 2007.} }