% AwesomeCUA: {"catalog_id": "arxiv:2403.10170", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2403.10170"}}
@misc{arxiv_2403_10170,
  title = {{Computer User Interface Understanding. A New Dataset and a Learning Framework}},
  author = {{Andrés Muñoz} and {Daniel Borrajo}},
  year = {2024},
  eprint = {2403.10170v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.10170v2},
  note = {First published: 2024-03-15; Recorded arXiv version: v2; Recorded version updated: 2024-08-27T18:36:12Z.}
}

% AwesomeCUA: {"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: {"canonical_source_url": "https://arxiv.org/abs/2406.10227", "catalog_id": "arxiv:2406.10227", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2406.10227"}, "publication": {"authors": ["Kevin Q. Lin", "Linjie Li", "Difei Gao", "Qinchen Wu", "Mingyi Yan", "Zhengyuan Yang", "Lijuan Wang", "Mike Z. Shou"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-2214", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "69329-69360", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/804e757b7d7043c26701c3a313032101-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "VideoGUI: A Benchmark for GUI Automation from Instructional Videos", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/804e757b7d7043c26701c3a313032101-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}}
@misc{arxiv_2406_10227,
  title = {{VideoGUI: A Benchmark for GUI Automation from Instructional Videos}},
  author = {{Kevin Qinghong Lin} and {Linjie Li} and {Difei Gao} and {Qinchen WU} and {Mingyi Yan} and {Zhengyuan Yang} and {Lijuan Wang} and {Mike Zheng Shou}},
  year = {2024},
  eprint = {2406.10227v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.10227v1},
  note = {First published: 2024-06-14; Recorded arXiv version: v1; Recorded version updated: 2024-06-14T17:59:08Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2406.10819", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.10819"}}
@misc{arxiv_2406_10819,
  title = {{GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding}},
  author = {{Dongping Chen} and {Yue Huang} and {Siyuan Wu} and {Jingyu Tang} and {Liuyi Chen} and {Yilin Bai} and {Zhigang He} and {Chenlong Wang} and {Huichi Zhou} and {Yiqiang Li} and {Tianshuo Zhou} and {Yue Yu} and {Chujie Gao} and {Qihui Zhang} and {Yi Gui} and {Zhen Li} and {Yao Wan} and {Pan Zhou} and {Jianfeng Gao} and {Lichao Sun}},
  year = {2024},
  eprint = {2406.10819v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.10819v2},
  note = {First published: 2024-06-16; Recorded arXiv version: v2; Recorded version updated: 2025-03-24T11:46:14Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2406.13264", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.13264"}}
@misc{arxiv_2406_13264,
  title = {{WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks}},
  author = {{Michael Wornow} and {Avanika Narayan} and {Ben Viggiano} and {Ishan S. Khare} and {Tathagat Verma} and {Tibor Thompson} and {Miguel Angel Fuentes Hernandez} and {Sudharsan Sundar} and {Chloe Trujillo} and {Krrish Chawla} and {Rongfei Lu} and {Justin Shen} and {Divya Nagaraj} and {Joshua Martinez} and {Vardhan Agrawal} and {Althea Hudson} and {Nigam H. Shah} and {Christopher Re}},
  year = {2024},
  eprint = {2406.13264v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.13264v2},
  note = {First published: 2024-06-19; Recorded arXiv version: v2; Recorded version updated: 2024-10-11T00:06:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2406.13719", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.13719"}}
@misc{arxiv_2406_13719,
  title = {{GUI Action Narrator: Where and When Did That Action Take Place?}},
  author = {{Qinchen Wu} and {Difei Gao} and {Kevin Qinghong Lin} and {Zhuoyu Wu} and {Xiangwu Guo} and {Peiran Li} and {Weichen Zhang} and {Hengxu Wang} and {Mike Zheng Shou}},
  year = {2024},
  eprint = {2406.13719v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.13719v1},
  note = {First published: 2024-06-19; Recorded arXiv version: v1; Recorded version updated: 2024-06-19T17:22:11Z.}
}

% AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2410.19100", "catalog_id": "arxiv:2410.19100", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2410.19100"}, "publication": {"authors": ["Lawrence Jang", "Yinheng Li", "Dan Zhao", "Charles Ding", "Justin Lin", "Paul Pu Liang", "Rogerio Bonatti", "Kazuhito Koishida"], "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 5, 1], "doi": null, "event_dates": null, "evidence_urls": ["https://proceedings.iclr.cc/paper_files/paper/2025/hash/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "36934-36958", "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/5b555804d495321df2e3208cc27f4fbc-Paper-Conference.pdf", "publisher": null, "series": null, "title": "VideoWebArena:  Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks", "type": "conference-paper", "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/5b555804d495321df2e3208cc27f4fbc-Abstract-Conference.html", "venue": "International Conference on Learning Representations", "volume": "2025"}}
@misc{arxiv_2410_19100,
  title = {{VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks}},
  author = {{Lawrence Jang} and {Yinheng Li} and {Dan Zhao} and {Charles Ding} and {Justin Lin} and {Paul Pu Liang} and {Rogerio Bonatti} and {Kazuhito Koishida}},
  year = {2024},
  eprint = {2410.19100v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.19100v3},
  note = {First published: 2024-10-24; Recorded arXiv version: v3; Recorded version updated: 2025-02-15T05:19:38Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2502.17110", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.17110"}}
@misc{arxiv_2502_17110,
  title = {{Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation}},
  author = {{Junyang Wang} and {Haiyang Xu} and {Xi Zhang} and {Ming Yan} and {Ji Zhang} and {Fei Huang} and {Jitao Sang}},
  year = {2025},
  eprint = {2502.17110v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.17110v3},
  note = {First published: 2025-02-24; Recorded arXiv version: v3; Recorded version updated: 2025-06-03T08:37:03Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2503.07919", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.07919"}}
@misc{arxiv_2503_07919,
  title = {{BEARCUBS: A benchmark for computer-using web agents}},
  author = {{Yixiao Song} and {Katherine Thai} and {Chau Minh Pham} and {Yapei Chang} and {Mazin Nadaf} and {Mohit Iyyer}},
  year = {2025},
  eprint = {2503.07919v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.07919v3},
  note = {First published: 2025-03-10; Recorded arXiv version: v3; Recorded version updated: 2025-07-24T17:45:05Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2503.17709", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2503.17709"}}
@misc{arxiv_2503_17709,
  title = {{GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration}},
  author = {{Yuchen Sun} and {Shanhui Zhao} and {Tao Yu} and {Hao Wen} and {Samith Va} and {Mengwei Xu} and {Yuanchun Li} and {Chongyang Zhang}},
  year = {2025},
  eprint = {2503.17709v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.17709v1},
  note = {First published: 2025-03-22; Recorded arXiv version: v1; Recorded version updated: 2025-03-22T09:30:37Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv: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:2505.12632", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.12632"}}
@misc{arxiv_2505_12632,
  title = {{Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents}},
  author = {{Yunseok Jang} and {Yeda Song} and {Sungryull Sohn} and {Lajanugen Logeswaran} and {Tiange Luo} and {Dong-Ki Kim} and {Kyunghoon Bae} and {Honglak Lee}},
  year = {2025},
  eprint = {2505.12632v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.12632v1},
  note = {First published: 2025-05-19; Recorded arXiv version: v1; Recorded version updated: 2025-05-19T02:39:03Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2505.24838", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.24838"}}
@misc{arxiv_2505_24838,
  title = {{VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video}},
  author = {{Brandon Man} and {Ghadi Nehme} and {Md Ferdous Alam} and {Faez Ahmed}},
  year = {2025},
  eprint = {2505.24838v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.24838v2},
  note = {First published: 2025-05-30; Recorded arXiv version: v2; Recorded version updated: 2025-11-08T18:27:03Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2510.19488", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.19488"}}
@misc{arxiv_2510_19488,
  title = {{VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos}},
  author = {{Dunjie Lu} and {Yiheng Xu} and {Junli Wang} and {Haoyuan Wu} and {Xinyuan Wang} and {Zekun Wang} and {Junlin Yang} and {Hongjin Su} and {Jixuan Chen} and {Junda Chen} and {Yuchen Mao} and {Jingren Zhou} and {Junyang Lin} and {Binyuan Hui} and {Tao Yu}},
  year = {2025},
  eprint = {2510.19488v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.19488v1},
  note = {First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T11:25:48Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2511.04137", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.04137"}}
@misc{arxiv_2511_04137,
  title = {{Learning from Online Videos at Inference Time for Computer-Use Agents}},
  author = {{Yujian Liu} and {Ze Wang} and {Hao Chen} and {Ximeng Sun} and {Xiaodong Yu} and {Jialian Wu} and {Jiang Liu} and {Emad Barsoum} and {Zicheng Liu} and {Shiyu Chang}},
  year = {2025},
  eprint = {2511.04137v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.04137v1},
  note = {First published: 2025-11-06; Recorded arXiv version: v1; Recorded version updated: 2025-11-06T07:29:02Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.10178", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.10178"}}
@misc{arxiv_2603_10178,
  title = {{Video-Based Reward Modeling for Computer-Use Agents}},
  author = {{Linxin Song} and {Jieyu Zhang} and {Huanxin Sheng} and {Taiwei Shi} and {Gupta Rahul} and {Yang Liu} and {Ranjay Krishna} and {Jian Kang} and {Jieyu Zhao}},
  year = {2026},
  eprint = {2603.10178v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.10178v1},
  note = {First published: 2026-03-10; Recorded arXiv version: v1; Recorded version updated: 2026-03-10T19:17:22Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.22529", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.22529"}}
@misc{arxiv_2603_22529,
  title = {{Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos}},
  author = {{Shoubin Yu} and {Lei Shu} and {Antoine Yang} and {Yao Fu} and {Srinivas Sunkara} and {Maria Wang} and {Jindong Chen} and {Mohit Bansal} and {Boqing Gong}},
  year = {2026},
  eprint = {2603.22529v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.22529v1},
  note = {First published: 2026-03-23; Recorded arXiv version: v1; Recorded version updated: 2026-03-23T19:47:58Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.24440", "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:2603.25864", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.25864"}}
@misc{arxiv_2603_25864,
  title = {{GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks}},
  author = {{Saelyne Yang} and {Jaesang Yu} and {Yi-Hao Peng} and {Kevin Qinghong Lin} and {Jae Won Cho} and {Yale Song} and {Juho Kim}},
  year = {2026},
  eprint = {2603.25864v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.25864v1},
  note = {First published: 2026-03-26; Recorded arXiv version: v1; Recorded version updated: 2026-03-26T19:37:53Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.26266", "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:2604.25380", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.25380"}}
@misc{arxiv_2604_25380,
  title = {{Benchmarking and Improving GUI Agents in High-Dynamic Environments}},
  author = {{Enqi Liu} and {Liyuan Pan} and {Zhi Gao} and {Yan Yang} and {Chenrui Shi} and {Yang Liu} and {Jingrong Wu} and {Qing Li}},
  year = {2026},
  eprint = {2604.25380v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.25380v2},
  note = {First published: 2026-04-28; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T04:29:20Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.26148", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.26148"}}
@misc{arxiv_2604_26148,
  title = {{Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations}},
  author = {{Chen Liang} and {Xirui Jiang} and {Naihao Deng} and {Eytan Adar} and {Anhong Guo}},
  year = {2026},
  eprint = {2604.26148v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.26148v3},
  note = {First published: 2026-04-28; Recorded arXiv version: v3; Recorded version updated: 2026-08-11T15:48:53Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2605.10966", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2605.10966"}}
@misc{arxiv_2605_10966,
  title = {{MMTB: Evaluating Terminal Agents on Multimedia-File Tasks}},
  author = {{Chiyeong Heo} and {Jaechang Kim} and {Junhyuk Kwon} and {Hoyoung Kim} and {Dongmin Park} and {Jonghyun Lee} and {Jungseul Ok}},
  year = {2026},
  eprint = {2605.10966v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.10966v1},
  note = {First published: 2026-05-08; Recorded arXiv version: v1; Recorded version updated: 2026-05-08T10:57:19Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2605.18758", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.18758"}}
@misc{arxiv_2605_18758,
  title = {{OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments}},
  author = {{Felix Henry} and {Lihan Lin} and {Jiangyou Zhu} and {Yangfan} and {Bingqian Zhang} and {Min Chen} and {Shiyu Huang}},
  year = {2026},
  eprint = {2605.18758v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.18758v2},
  note = {First published: 2026-04-03; Recorded arXiv version: v2; Recorded version updated: 2026-09-28T02:42:06Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.04701", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.04701"}}
@misc{arxiv_2606_04701,
  title = {{Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms}},
  author = {{Jiashu Yao} and {Heyan Huang} and {Daiqing Wu} and {Wangke Chen} and {Huaxi Ai} and {Haoyu Wen} and {Zeming Liu} and {Yuhang Guo}},
  year = {2026},
  eprint = {2606.04701v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.04701v1},
  note = {First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T10:25:46Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.29472", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.29472"}}
@misc{arxiv_2606_29472,
  title = {{Agent-Computer Observation Interfaces Enable Dynamic Computer Use}},
  author = {{Bojie Li} and {Noah Shi}},
  year = {2026},
  eprint = {2606.29472v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.29472v1},
  note = {First published: 2026-06-28; Recorded arXiv version: v1; Recorded version updated: 2026-06-28T15:59:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.31980", "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:2609.27461", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.27461"}}
@misc{arxiv_2609_27461,
  title = {{Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents}},
  author = {{Zeyu Zhang} and {Dingyi Rong} and {Zijian Chen} and {Zicheng Zhang} and {Xiongkuo Min} and {Guangtao Zhai}},
  year = {2026},
  eprint = {2609.27461v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27461v1},
  note = {First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T07:27:23Z.}
}