% AwesomeCUA: {"catalog_id": "arxiv:2402.06596", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2402.06596"}}
@misc{arxiv_2402_06596,
  title = {{Understanding the Weakness of Large Language Model Agents within a Complex Android Environment}},
  author = {{Mingzhe Xing} and {Rongkai Zhang} and {Hui Xue} and {Qi Chen} and {Fan Yang} and {Zhen Xiao}},
  year = {2024},
  eprint = {2402.06596v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.06596v1},
  note = {First published: 2024-02-09; Recorded arXiv version: v1; Recorded version updated: 2024-02-09T18:19:25Z.}
}

% AwesomeCUA: {"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: {"canonical_source_url": "https://arxiv.org/abs/2404.07972", "catalog_id": "arxiv:2404.07972", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2404.07972"}, "publication": {"authors": ["Tianbao Xie", "Danyang Zhang", "Jixuan Chen", "Xiaochuan Li", "Siheng Zhao", "Ruisheng Cao", "Toh J. Hua", "Zhoujun Cheng", "Dongchan Shin", "Fangyu Lei", "Yitao Liu", "Yiheng Xu", "Shuyan Zhou", "Silvio Savarese", "Caiming Xiong", "Victor Zhong", "Tao Yu"], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2024, 12, 16], "doi": "10.52202/079017-1650", "event_dates": null, "evidence_urls": ["https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-Abstract-Datasets_and_Benchmarks_Track.html"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "52040-52094", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/5d413e48f84dc61244b6be550f1cd8f5-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/5d413e48f84dc61244b6be550f1cd8f5-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37"}}
@misc{arxiv_2404_07972,
  title = {{OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments}},
  author = {{Tianbao Xie} and {Danyang Zhang} and {Jixuan Chen} and {Xiaochuan Li} and {Siheng Zhao} and {Ruisheng Cao} and {Toh Jing Hua} and {Zhoujun Cheng} and {Dongchan Shin} and {Fangyu Lei} and {Yitao Liu} and {Yiheng Xu} and {Shuyan Zhou} and {Silvio Savarese} and {Caiming Xiong} and {Victor Zhong} and {Tao Yu}},
  year = {2024},
  eprint = {2404.07972v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.07972v2},
  note = {First published: 2024-04-11; Recorded arXiv version: v2; Recorded version updated: 2024-05-30T08:55:12Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2406.08340", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.08340"}}
@misc{arxiv_2406_08340,
  title = {{Practical, Automated Scenario-based Mobile App Testing}},
  author = {{Shengcheng Yu} and {Chunrong Fang} and {Mingzhe Du} and {Zimin Ding} and {Zhenyu Chen} and {Zhendong Su}},
  year = {2024},
  eprint = {2406.08340v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.08340v1},
  note = {First published: 2024-06-12; Recorded arXiv version: v1; Recorded version updated: 2024-06-12T15:48:39Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2406.08451", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.08451"}}
@misc{arxiv_2406_08451,
  title = {{GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices}},
  author = {{Quanfeng Lu} and {Wenqi Shao} and {Zitao Liu} and {Lingxiao Du} and {Fanqing Meng} and {Boxuan Li} and {Botong Chen} and {Siyuan Huang} and {Kaipeng Zhang} and {Ping Luo}},
  year = {2024},
  eprint = {2406.08451v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.08451v2},
  note = {First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2025-08-01T03:37:57Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2407.00993", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.00993"}}
@misc{arxiv_2407_00993,
  title = {{Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents}},
  author = {{Shihan Deng} and {Weikai Xu} and {Hongda Sun} and {Wei Liu} and {Tao Tan} and {Jianfeng Liu} and {Ang Li} and {Jian Luan} and {Bin Wang} and {Rui Yan} and {Shuo Shang}},
  year = {2024},
  eprint = {2407.00993v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.00993v1},
  note = {First published: 2024-07-01; Recorded arXiv version: v1; Recorded version updated: 2024-07-01T06:10:01Z.}
}

% AwesomeCUA: {"canonical_source_url": "https://arxiv.org/abs/2407.01511", "catalog_id": "arxiv:2407.01511", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "identifiers": {"arxiv": "2407.01511"}, "publication": {"authors": ["Tianqi Xu", "Linyao Chen", "Dai-Jie Wu", "Yanjun Chen", "Zecheng Zhang", "Xiang Yao", "Zhiqiang Xie (\u8c22\u5fd7\u5f3a)", "Yongchao Chen", "Shilong Liu", "Bochen Qian", "Anjie Yang", "Zhaoxuan Jin", "Jianbo Deng", "Philip Torr", "Bernard Ghanem", "Guohao Li"], "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [2025, 7], "doi": "10.18653/v1/2025.findings-acl.1113", "event_dates": null, "evidence_urls": ["https://aclanthology.org/2025.findings-acl.1113/"], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.", "pages": "21607-21647", "pdf_url": "https://aclanthology.org/2025.findings-acl.1113.pdf", "publisher": "Association for Computational Linguistics", "series": null, "title": "CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents", "type": "conference-paper", "url": "https://aclanthology.org/2025.findings-acl.1113/", "venue": "Findings of the Association for Computational Linguistics: ACL 2025", "volume": null}}
@misc{arxiv_2407_01511,
  title = {{CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents}},
  author = {{Tianqi Xu} and {Linyao Chen} and {Dai-Jie Wu} and {Yanjun Chen} and {Zecheng Zhang} and {Xiang Yao} and {Zhiqiang Xie} and {Yongchao Chen} and {Shilong Liu} and {Bochen Qian} and {Anjie Yang} and {Zhaoxuan Jin} and {Jianbo Deng} and {Philip Torr} and {Bernard Ghanem} and {Guohao Li}},
  year = {2024},
  eprint = {2407.01511v4},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.01511v4},
  note = {First published: 2024-07-01; Recorded arXiv version: v4; Recorded version updated: 2025-07-20T13:42:07Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2407.18901", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2407.18901"}}
@misc{arxiv_2407_18901,
  title = {{AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents}},
  author = {{Harsh Trivedi} and {Tushar Khot} and {Mareike Hartmann} and {Ruskin Manku} and {Vinty Dong} and {Edward Li} and {Shashank Gupta} and {Ashish Sabharwal} and {Niranjan Balasubramanian}},
  year = {2024},
  eprint = {2407.18901v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.18901v1},
  note = {First published: 2024-07-26; Recorded arXiv version: v1; Recorded version updated: 2024-07-26T17:55:45Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2407.19056", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2407.19056"}}
@misc{arxiv_2407_19056,
  title = {{OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation}},
  author = {{Zilong Wang} and {Yuedong Cui} and {Li Zhong} and {Zimin Zhang} and {Da Yin} and {Bill Yuchen Lin} and {Jingbo Shang}},
  year = {2024},
  eprint = {2407.19056v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.19056v1},
  note = {First published: 2024-07-26; Recorded arXiv version: v1; Recorded version updated: 2024-07-26T19:27:17Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2409.08264", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2409.08264"}}
@misc{arxiv_2409_08264,
  title = {{Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale}},
  author = {{Rogerio Bonatti} and {Dan Zhao} and {Francesco Bonacci} and {Dillon Dupont} and {Sara Abdali} and {Yinheng Li} and {Yadong Lu} and {Justin Wagle} and {Kazuhito Koishida} and {Arthur Bucker} and {Lawrence Jang} and {Zack Hui}},
  year = {2024},
  eprint = {2409.08264v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.08264v2},
  note = {First published: 2024-09-12; Recorded arXiv version: v2; Recorded version updated: 2024-09-13T20:17:13Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2502.14282", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2502.14282"}}
@misc{arxiv_2502_14282,
  title = {{PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC}},
  author = {{Haowei Liu} and {Xi Zhang} and {Haiyang Xu} and {Yuyang Wanyan} and {Junyang Wang} and {Ming Yan} and {Ji Zhang} and {Chunfeng Yuan} and {Changsheng Xu} and {Weiming Hu} and {Fei Huang}},
  year = {2025},
  eprint = {2502.14282v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.14282v2},
  note = {First published: 2025-02-20; Recorded arXiv version: v2; Recorded version updated: 2025-02-21T02:54:09Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2504.02357", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.02357"}}
@misc{arxiv_2504_02357,
  title = {{ReuseDroid: A VLM-empowered Android UI Test Migrator Boosted by Active Feedback}},
  author = {{Xiaolei Li} and {Jialun Cao} and {Yepang Liu} and {Shing-Chi Cheung} and {Hailong Wang}},
  year = {2025},
  eprint = {2504.02357v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.02357v1},
  note = {First published: 2025-04-03; Recorded arXiv version: v1; Recorded version updated: 2025-04-03T07:45:09Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2504.14603", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2504.14603"}}
@misc{arxiv_2504_14603,
  title = {{UFO2: The Desktop AgentOS}},
  author = {{Chaoyun Zhang} and {He Huang} and {Chiming Ni} and {Jian Mu} and {Si Qin} and {Shilin He} and {Lu Wang} and {Fangkai Yang} and {Pu Zhao} and {Chao Du} and {Liqun Li} and {Yu Kang} and {Zhao Jiang} and {Suzhen Zheng} and {Rujia Wang} and {Jiaxu Qian} and {Minghua Ma} and {Jian-Guang Lou} and {Qingwei Lin} and {Saravan Rajmohan} and {Dongmei Zhang}},
  year = {2025},
  eprint = {2504.14603v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.14603v2},
  note = {First published: 2025-04-20; Recorded arXiv version: v2; Recorded version updated: 2025-04-25T05:14:14Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2505.03570", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.03570"}}
@misc{arxiv_2505_03570,
  title = {{OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents}},
  author = {{Mariya Davydova} and {Daniel Jeffries} and {Patrick Barker} and {Arturo Márquez Flores} and {Sinéad Ryan}},
  year = {2025},
  eprint = {2505.03570v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.03570v1},
  note = {First published: 2025-05-06; Recorded arXiv version: v1; Recorded version updated: 2025-05-06T14:29:47Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2505.10831", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2505.10831"}}
@misc{arxiv_2505_10831,
  title = {{Creating General User Models from Computer Use}},
  author = {{Omar Shaikh} and {Shardul Sapkota} and {Shan Rizvi} and {Eric Horvitz} and {Joon Sung Park} and {Diyi Yang} and {Michael S. Bernstein}},
  year = {2025},
  eprint = {2505.10831v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.10831v3},
  note = {First published: 2025-05-16; Recorded arXiv version: v3; Recorded version updated: 2025-09-21T00:03:34Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2506.18158", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.18158"}}
@misc{arxiv_2506_18158,
  title = {{Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation}},
  author = {{Xinzge Gao} and {Chuanrui Hu} and {Bin Chen} and {Teng Li}},
  year = {2025},
  eprint = {2506.18158v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.18158v1},
  note = {First published: 2025-06-22; Recorded arXiv version: v1; Recorded version updated: 2025-06-22T20:17:46Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.15738", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.15738"}}
@misc{arxiv_2509_15738,
  title = {{GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning}},
  author = {{Musen Lin} and {Minghao Liu} and {Taoran Lu} and {Lichen Yuan} and {Yiwei Liu} and {Haonan Xu} and {Yu Miao} and {Yuhao Chao} and {Zhaojian Li}},
  year = {2025},
  eprint = {2509.15738v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.15738v1},
  note = {First published: 2025-09-19; Recorded arXiv version: v1; Recorded version updated: 2025-09-19T08:09:18Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2601.02399", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.02399"}}
@misc{arxiv_2601_02399,
  title = {{ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments}},
  author = {{Jiaxin Ai} and {Yukang Feng} and {Fanrui Zhang} and {Jianwen Sun} and {Zizhen Li} and {Chuanhao Li} and {Yifan Chang} and {Wenxiao Wu} and {Ruoxi Wang} and {Mingliang Zhai} and {Kaipeng Zhang}},
  year = {2025},
  eprint = {2601.02399v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.02399v1},
  note = {First published: 2025-12-30; Recorded arXiv version: v1; Recorded version updated: 2025-12-30T01:49:46Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2601.12349", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.12349"}}
@misc{arxiv_2601_12349,
  title = {{Mind the Gap: Action Rebinding Attacks against Android GUI Agents}},
  author = {{Yi Qian} and {Kunwei Qian} and {Xingbang He} and {Ligeng Chen} and {Jikang Zhang} and {Tiantai Zhang} and {Haiyang Wei} and {Linzhang Wang} and {Hao Wu} and {Bing Mao}},
  year = {2026},
  eprint = {2601.12349v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.12349v3},
  note = {First published: 2026-01-18; Recorded arXiv version: v3; Recorded version updated: 2026-07-15T15:32:11Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2601.22528", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.22528"}}
@misc{arxiv_2601_22528,
  title = {{Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution}},
  author = {{Hongze Mi} and {Yibo Feng} and {WenJie Lu} and {Song Cao} and {Jinyuan Li} and {Yanming Li} and {Xuelin Zhang} and {Haotian Luo} and {Songyang Peng} and {He Cui} and {Tengfei Tian} and {Jun Fang} and {Hua Chai} and {Naiqiang Tan}},
  year = {2026},
  eprint = {2601.22528v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.22528v1},
  note = {First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T04:01:21Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2602.05832", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.05832"}}
@misc{arxiv_2602_05832,
  title = {{UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents}},
  author = {{Han Xiao} and {Guozhi Wang} and {Hao Wang} and {Shilong Liu} and {Yuxiang Chai} and {Yue Pan} and {Yufeng Zhou} and {Xiaoxin Chen} and {Yafei Wen} and {Hongsheng Li}},
  year = {2026},
  eprint = {2602.05832v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.05832v1},
  note = {First published: 2026-02-05; Recorded arXiv version: v1; Recorded version updated: 2026-02-05T16:21:43Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2602.06075", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.06075"}}
@misc{arxiv_2602_06075,
  title = {{MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments}},
  author = {{Guangyi Liu} and {Pengxiang Zhao} and {Yaozhen Liang} and {Qinyi Luo} and {Shunye Tang} and {Yuxiang Chai} and {Weifeng Lin} and {Han Xiao} and {WenHao Wang} and {Siheng Chen} and {Zhengxi Lu} and {Gao Wu} and {Hao Wang} and {Liang Liu} and {Yong Liu}},
  year = {2026},
  eprint = {2602.06075v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.06075v3},
  note = {First published: 2026-02-03; Recorded arXiv version: v3; Recorded version updated: 2026-08-27T06:48:18Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.27776", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.27776"}}
@misc{arxiv_2604_27776,
  title = {{WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments}},
  author = {{Jinchao Li} and {Yunxin Li} and {Chenrui Zhao} and {Zhenran Xu} and {Baotian Hu} and {Min Zhang}},
  year = {2026},
  eprint = {2604.27776v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.27776v1},
  note = {First published: 2026-04-30; Recorded arXiv version: v1; Recorded version updated: 2026-04-30T12:13:27Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2605.15777", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.15777"}}
@misc{arxiv_2605_15777,
  title = {{SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?}},
  author = {{Kean Shi} and {Zihang Li} and {Tianyi Ma} and {Zengji Tu} and {Jialong Wu} and {Xinbo Xu} and {Qingyao Yang} and {Ruoyu Wu} and {Weichu Xie} and {Ming Wu} and {Jason Zeng} and {Michael Heinrich} and {Elvis Zhang} and {Liang Chen} and {Kuan Li} and {Baobao Chang}},
  year = {2026},
  eprint = {2605.15777v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.15777v2},
  note = {First published: 2026-05-15; Recorded arXiv version: v2; Recorded version updated: 2026-05-24T16:35:56Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.09764", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.09764"}}
@misc{arxiv_2606_09764,
  title = {{iOSWorld: A Benchmark for Personally Intelligent Phone Agents}},
  author = {{Lawrence Keunho Jang} and {Mareks Woodside} and {Geronimo Carom} and {Andrew Keunwoo Jang} and {Jing Yu Koh} and {Ruslan Salakhutdinov}},
  year = {2026},
  eprint = {2606.09764v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.09764v1},
  note = {First published: 2026-06-08; Recorded arXiv version: v1; Recorded version updated: 2026-06-08T17:27:13Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.16748", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.16748"}}
@misc{arxiv_2606_16748,
  title = {{MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents}},
  author = {{Lawrence Keunho Jang} and {Andrew Keunwoo Jang} and {Jing Yu Koh} and {Ruslan Salakhutdinov}},
  year = {2026},
  eprint = {2606.16748v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.16748v1},
  note = {First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T14:08:09Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.19388", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2606.19388"}}
@misc{arxiv_2606_19388,
  title = {{Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?}},
  author = {{Li Gu} and {Zihuan Jiang} and {Linqiang Guo} and {Zhixiang Chi} and {Ziqiang Wang} and {Huan Liu} and {Yuanhao Yu} and {Tse-Hsun Chen} and {Yang Wang}},
  year = {2026},
  eprint = {2606.19388v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.19388v1},
  note = {First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T02:36:22Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.22557", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.22557"}}
@misc{arxiv_2606_22557,
  title = {{MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop}},
  author = {{Yikun Fu} and {Bowen Fu} and {Zhenyu Wu} and {Shuang Cheng} and {Xiaowei Sun} and {Bowen Yang} and {Zehao Li} and {Yibo Zhao} and {Zichen Ding} and {Zhoumianze Liu} and {Shijie Wang} and {Biqing Qi} and {Bowen Zhou}},
  year = {2026},
  eprint = {2606.22557v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.22557v1},
  note = {First published: 2026-06-21; Recorded arXiv version: v1; Recorded version updated: 2026-06-21T15:32:57Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.23189", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.23189"}}
@misc{arxiv_2606_23189,
  title = {{Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?}},
  author = {{Anmol Goel} and {Iryna Gurevych}},
  year = {2026},
  eprint = {2606.23189v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.23189v2},
  note = {First published: 2026-06-22; Recorded arXiv version: v2; Recorded version updated: 2026-09-10T18:49:54Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2608.08392", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.08392"}}
@misc{arxiv_2608_08392,
  title = {{CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception}},
  author = {{Zejun Xu} and {Taiyi Chen} and {Jin Li} and {Yongtong Gu} and {Qi Cheng} and {Aixuan Lv} and {Shuai Zhu} and {Pengfei Zhu} and {Kaichen Yang} and {Boyu Sun} and {Yixian Yang} and {Mulong Xie} and {Xin Liu} and {Dagang Li} and {Xiaoteng Ma} and {Hongru Wang}},
  year = {2026},
  eprint = {2608.08392v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.08392v1},
  note = {First published: 2026-08-09; Recorded arXiv version: v1; Recorded version updated: 2026-08-09T01:08:19Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.10451", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.10451"}}
@misc{arxiv_2609_10451,
  title = {{JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition}},
  author = {{Zixiang Chen} and {Yuheng Lu} and {Zihao Cheng} and {Zeming Liu} and {Jizeng Bai} and {Ziye Huang} and {Zhiyin Lin} and {Zihan Li} and {Yuhang Guo} and {Yunhong Wang} and {Haifeng Wang}},
  year = {2026},
  eprint = {2609.10451v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.10451v1},
  note = {First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T16:59:59Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.37053", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.37053"}}
@misc{arxiv_2609_37053,
  title = {{MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows}},
  author = {{Mei Wu} and {Rui Xie} and {Runyu Zhang} and {Yuqiang Li} and {Tianfan Fu} and {Bo Chen} and {Kai Yu} and {Xin Chen} and {Lu Chen}},
  year = {2026},
  eprint = {2609.37053v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.37053v1},
  note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T08:58:51Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.37686", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.37686"}}
@misc{arxiv_2609_37686,
  title = {{EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?}},
  author = {{Hongcheng Gao} and {Hailong Qu} and {Yu Lei} and {Henghui Sun} and {Haoyang Li} and {Yipeng Wei} and {Naihao Xue} and {Xiaohan Yu} and {Zhuo Tao} and {Yihe Zang} and {Yajiao Wang} and {Jingyi Tang} and {Yi Li} and {Jingjing Zhou} and {Jie Luo} and {Bohan Zeng} and {Chengyu Shen} and {Hao Jiang} and {Chong Chen} and {Bowen Qu} and {Olive Huang} and {Zeqiang Wang}},
  year = {2026},
  eprint = {2609.37686v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.37686v2},
  note = {First published: 2026-09-29; Recorded arXiv version: v2; Recorded version updated: 2026-10-09T08:15:21Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.11050", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.11050"}}
@misc{arxiv_2610_11050,
  title = {{AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks}},
  author = {{Xing Han Lù} and {Dheeraj Vattikonda} and {Sina Hajimiri} and {Fatemeh Pesaran Zadeh} and {Parishad BehnamGhader} and {Ghazwa Darwiche} and {Amirhossein Kazemnejad} and {Christopher Pal} and {Alexandre Drouin} and {Siva Reddy}},
  year = {2026},
  eprint = {2610.11050v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.11050v1},
  note = {First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T01:03:48Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.23303", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.23303"}}
@misc{arxiv_2610_23303,
  title = {{MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents}},
  author = {{Songping Wang} and {Borui Li} and {Qinglong Liu} and {Yueming Lyu} and {Yi Huang} and {Fengting Li} and {Chao Feng} and {Caifeng Shan}},
  year = {2026},
  eprint = {2610.23303v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.23303v1},
  note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T11:06:37Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.23307", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.23307"}}
@misc{arxiv_2610_23307,
  title = {{MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection}},
  author = {{Songping Wang} and {Peiyang Li} and {Yi Huang} and {Fengting Li} and {Xuhao Ran} and {Yueming Lyu} and {Chao Feng} and {Caifeng Shan}},
  year = {2026},
  eprint = {2610.23307v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.23307v1},
  note = {First published: 2026-10-16; Recorded arXiv version: v1; Recorded version updated: 2026-10-16T11:10:30Z.}
}

% AwesomeCUA: {"canonical_source_url": "https://doi.org/10.1145/3025453.3025483", "catalog_id": "url:392a602c660ffa91be46", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "publication", "identifiers": {"doi": "10.1145/3025453.3025483"}, "publication": {"authors": ["Toby Jia-Jun Li", "Amos Azaria", "Brad A. Myers"], "date_basis": "Supplied year precision: 2017. Publications: SUGILITE, CHI 2017 Only publication year is asserted; event dates are kept separate.", "date_parts": [2017], "doi": "10.1145/3025453.3025483", "event_dates": null, "evidence_urls": ["https://www.cs.cmu.edu/~NatProg/sugilite.html", "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf"], "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.", "issue": null, "notes": "Related to later APPINITE and PUMICE work but distinguished here by its 2017 three-author publication and base demonstration-automation contribution. Publication month/day are not independently identified by the retained sources.", "pages": "6038-6049", "pdf_url": "https://toby.li/files/TobyLi-CHI2017-Sugilite.pdf", "publisher": null, "series": null, "title": "SUGILITE: Creating Multimodal Smartphone Automation by Demonstration", "type": "conference-paper", "url": "https://doi.org/10.1145/3025453.3025483", "venue": "Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems", "volume": null}}
@inproceedings{cua_6b7f9d608ed89d1625610eb1,
  title = {{SUGILITE: Creating Multimodal Smartphone Automation by Demonstration}},
  author = {{Toby Jia-Jun Li} and {Amos Azaria} and {Brad A. Myers}},
  year = {2017},
  booktitle = {Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems},
  pages = {6038-6049},
  doi = {10.1145/3025453.3025483},
  url = {https://doi.org/10.1145/3025453.3025483},
  note = {Publication date: 2017.}
}