% 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: {"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: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: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: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: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: {"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: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:2310.11441", "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: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: {"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: {"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: {"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: {"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: {"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: {"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:2402.17553", "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: {"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:2403.17918", "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:2404.05719", "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:2404.05955", "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:2404.16048", "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: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: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/2406.14056", "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: {"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:2407.01558", "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: {"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: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: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:2409.10811", "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:2409.12089", "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: {"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:2410.11871", "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: {"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:2410.18967", "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: {"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: {"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: {"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:2411.13591", "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: {"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: {"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:2412.10342", "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: {"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: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:2501.12326", "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: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: {"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: {"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:2503.03196", "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:2503.04730", "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:2503.06470", "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:2503.11170", "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:2503.14021", "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:2503.15661", "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:2503.21620", "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: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:2504.04716", "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:2504.07981", "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:2504.09352", "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:2504.10445", "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:2504.12679", "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:2504.16073", "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: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:2505.12370", "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:2505.13227", "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:2505.15259", "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:2505.15810", "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:2505.21279", "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: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:2506.03143", "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:2506.09373", "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:2506.11127", "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:2506.15425", "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:2506.17913", "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:2506.23491", "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:2507.05673", "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:2507.05791", "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:2507.06899", "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:2507.15846", "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:2507.19478", "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:2507.22025", "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:2507.23779", "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:2508.04037", "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:2508.05615", "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:2508.09241", "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:2508.13634", "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:2508.16987", "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:2508.21767", "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:2509.02444", "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:2509.04243", "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:2509.11548", "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:2509.13615", "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:2509.15532", "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:2509.17328", "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:2509.21552", "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:2509.24133", "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:2509.26539", "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:2510.03230", "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:2510.04039", "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:2510.18488", "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:2510.20286", "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:2510.27266", "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:2511.04307", "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:2511.06417", "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:2511.10705", "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:2511.13087", "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:2511.21398", "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: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:2512.01979", "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:2512.05941", "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:2512.08529", "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:2512.16501", "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:2512.22009", "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:2512.24965", "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:2601.03928", "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:2601.09770", "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:2601.11631", "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:2601.18842", "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:2601.20380", "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:2601.20732", "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: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:2602.06351", "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:2602.09007", "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:2602.09082", "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:2602.10814", "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:2602.13653", "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:2602.14276", "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: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:2603.12823", "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:2603.17441", "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:2603.19993", "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:2603.24440", "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:2603.26211", "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: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:2604.07831", "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:2604.09581", "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:2604.13019", "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:2604.14113", "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:2604.17284", "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:2604.21268", "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:2604.23941", "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:2604.24441", "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: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:2605.02630", "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:2605.05765", "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:2605.12501", "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:2605.15542", "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:2605.16402", "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:2605.17656", "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: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:2606.09399", "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:2606.10522", "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:2606.11078", "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:2606.14106", "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:2606.18101", "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:2606.25760", "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:2606.29705", "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:2606.30697", "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:2606.31980", "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:2607.10079", "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:2607.14443", "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:2607.29320", "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:2608.03270", "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:2608.03740", "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:2608.09654", "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:2608.21794", "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:2608.21832", "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:2608.27866", "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: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:2609.13287", "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:2609.15307", "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:2609.16635", "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:2609.18690", "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:2609.22083", "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:2609.24277", "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:2609.27353", "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:2609.31957", "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:2609.32385", "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:2609.33646", "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:2609.35904", "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:2609.36939", "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: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:2610.02320", "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:2610.05185", "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:2610.07444", "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:2610.09240", "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:2610.12866", "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:2610.13268", "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:2610.15738", "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:2610.16720", "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:2610.17792", "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:2610.19100", "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:2610.19384", "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:2610.20107", "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:2610.26203", "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: {"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://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://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.}
}