% AwesomeCUA: {"catalog_id": "arxiv:2401.13178", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2401.13178"}}
@misc{arxiv_2401_13178,
  title = {{AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents}},
  author = {{Chang Ma} and {Junlei Zhang} and {Zhihao Zhu} and {Cheng Yang} and {Yujiu Yang} and {Yaohui Jin} and {Zhenzhong Lan} and {Lingpeng Kong} and {Junxian He}},
  year = {2024},
  eprint = {2401.13178v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.13178v2},
  note = {First published: 2024-01-24; Recorded arXiv version: v2; Recorded version updated: 2024-12-23T20:12:48Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2406.01623", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2406.01623"}}
@misc{arxiv_2406_01623,
  title = {{WebSuite: Systematically Evaluating Why Web Agents Fail}},
  author = {{Eric Li} and {Jim Waldo}},
  year = {2024},
  eprint = {2406.01623v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.01623v1},
  note = {First published: 2024-06-01; Recorded arXiv version: v1; Recorded version updated: 2024-06-01T00:32:26Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2506.16042", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2506.16042"}}
@misc{arxiv_2506_16042,
  title = {{OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents}},
  author = {{Reyna Abhyankar} and {Qi Qi} and {Yiying Zhang}},
  year = {2025},
  eprint = {2506.16042v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.16042v2},
  note = {First published: 2025-06-19; Recorded arXiv version: v2; Recorded version updated: 2026-05-18T17:55:59Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv: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:2508.14104", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.14104"}}
@misc{arxiv_2508_14104,
  title = {{You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation}},
  author = {{Yutong Bian} and {Xianhao Lin} and {Yupeng Xie} and {Tianyang Liu} and {Mingchen Zhuge} and {Siyuan Lu} and {Haoming Tang} and {Jinlin Wang} and {Jiayi Zhang} and {Jiaqi Chen} and {Xiangru Tang} and {Yongxin Ni} and {Sirui Hong} and {Chenglin Wu}},
  year = {2025},
  eprint = {2508.14104v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.14104v1},
  note = {First published: 2025-08-17; Recorded arXiv version: v1; Recorded version updated: 2025-08-17T07:31:11Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.07764", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.07764"}}
@misc{arxiv_2509_07764,
  title = {{AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents}},
  author = {{Haitao Hu} and {Peng Chen} and {Yanpeng Zhao} and {Yuqi Chen}},
  year = {2025},
  eprint = {2509.07764v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.07764v1},
  note = {First published: 2025-09-09; Recorded arXiv version: v1; Recorded version updated: 2025-09-09T13:59:00Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.14382", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.14382"}}
@misc{arxiv_2509_14382,
  title = {{Detecting Pipeline Failures through Fine-Grained Analysis of Web Agents}},
  author = {{Daniel Röder} and {Akhil Juneja} and {Roland Roller} and {Sven Schmeier}},
  year = {2025},
  eprint = {2509.14382v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.14382v1},
  note = {First published: 2025-09-17; Recorded arXiv version: v1; Recorded version updated: 2025-09-17T19:34:49Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.20729", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.20729"}}
@misc{arxiv_2509_20729,
  title = {{Robust, Observable, and Evolvable Agentic Systems Engineering: A Principled Framework Validated via the Fairy GUI Agent}},
  author = {{Jiazheng Sun} and {Ruimeng Yang} and {Xu Han} and {Jiayang Niu} and {Mingxuan Li} and {Te Yang} and {Yongyong Lu} and {Xin Peng}},
  year = {2025},
  eprint = {2509.20729v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.20729v2},
  note = {First published: 2025-09-25; Recorded arXiv version: v2; Recorded version updated: 2025-12-01T08:01:05Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2510.19205", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.19205"}}
@misc{arxiv_2510_19205,
  title = {{WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation}},
  author = {{Yaoyao Qian} and {Yuanli Wang} and {Jinda Zhang} and {Yun Zong} and {Meixu Chen} and {Hanhan Zhou} and {Jindan Huang} and {Yifan Zeng} and {Xinyu Hu} and {Chan Hee Song} and {Danqing Zhang}},
  year = {2025},
  eprint = {2510.19205v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.19205v1},
  note = {First published: 2025-10-22; Recorded arXiv version: v1; Recorded version updated: 2025-10-22T03:29:25Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2511.09157", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.09157"}}
@misc{arxiv_2511_09157,
  title = {{ProBench: Benchmarking GUI Agents with Accurate Process Information}},
  author = {{Leyang Yang} and {Ziwei Wang} and {Xiaoxuan Tang} and {Sheng Zhou} and {Dajun Chen} and {Wei Jiang} and {Yong Li}},
  year = {2025},
  eprint = {2511.09157v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.09157v1},
  note = {First published: 2025-11-12; Recorded arXiv version: v1; Recorded version updated: 2025-11-12T09:49:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2511.15567", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2511.15567"}}
@misc{arxiv_2511_15567,
  title = {{Computer-Use Agents as Judges for Generative User Interface}},
  author = {{Kevin Qinghong Lin} and {Siyuan Hu} and {Linjie Li} and {Zhengyuan Yang} and {Lijuan Wang} and {Philip Torr} and {Mike Zheng Shou}},
  year = {2025},
  eprint = {2511.15567v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.15567v1},
  note = {First published: 2025-11-19; Recorded arXiv version: v1; Recorded version updated: 2025-11-19T16:00:02Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2512.12634", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.12634"}}
@misc{arxiv_2512_12634,
  title = {{MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents}},
  author = {{Youngmin Im} and {Byeongung Jo} and {Jaeyoung Wi} and {Seungwoo Baek} and {Tae Hoon Min} and {Joo Hyung Lee} and {Sangeun Oh} and {Insik Shin} and {Sunjae Lee}},
  year = {2025},
  eprint = {2512.12634v4},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.12634v4},
  note = {First published: 2025-12-14; Recorded arXiv version: v4; Recorded version updated: 2026-05-31T23:48:10Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.10577", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.10577"}}
@misc{arxiv_2603_10577,
  title = {{CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents}},
  author = {{Marta Sumyk} and {Oleksandr Kosovan}},
  year = {2026},
  eprint = {2603.10577v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.10577v2},
  note = {First published: 2026-03-11; Recorded arXiv version: v2; Recorded version updated: 2026-03-12T07:30:09Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.10664", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2603.10664"}}
@misc{arxiv_2603_10664,
  title = {{Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration}},
  author = {{Alexandre De Masi}},
  year = {2026},
  eprint = {2603.10664v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.10664v1},
  note = {First published: 2026-03-11; Recorded arXiv version: v1; Recorded version updated: 2026-03-11T11:24:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.16520", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2604.16520"}}
@misc{arxiv_2604_16520,
  title = {{AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents}},
  author = {{Haomin Zhuang} and {Hanwen Xing} and {Xiangliang Zhang}},
  year = {2026},
  eprint = {2604.16520v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.16520v1},
  note = {First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T18:22:50Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2605.19769", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2605.19769"}}
@misc{arxiv_2605_19769,
  title = {{OpenComputer: Verifiable Software Worlds for Computer-Use Agents}},
  author = {{Jinbiao Wei} and {Qianran Ma} and {Yilun Zhao} and {Xiao Zhou} and {Kangqi Ni} and {Guo Gan} and {Arman Cohan}},
  year = {2026},
  eprint = {2605.19769v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.19769v1},
  note = {First published: 2026-05-19; Recorded arXiv version: v1; Recorded version updated: 2026-05-19T12:40:29Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.07594", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.07594"}}
@misc{arxiv_2606_07594,
  title = {{Syll: Open-Source Personal Automation with Cross-Surface Execution}},
  author = {{Bo Zhang} and {Borui Zhang} and {Chenghao Jiang} and {Minglei Shi} and {Xiaofeng Wang} and {Zheng Zhu} and {Jie Zhou} and {Jiwen Lu}},
  year = {2026},
  eprint = {2606.07594v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.07594v1},
  note = {First published: 2026-05-28; Recorded arXiv version: v1; Recorded version updated: 2026-05-28T17:59:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.18671", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.18671"}}
@misc{arxiv_2606_18671,
  title = {{HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification}},
  author = {{Yujin Zhang} and {Daye Nam}},
  year = {2026},
  eprint = {2606.18671v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.18671v1},
  note = {First published: 2026-06-17; Recorded arXiv version: v1; Recorded version updated: 2026-06-17T04:13:20Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.20910", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.20910"}}
@misc{arxiv_2606_20910,
  title = {{Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents}},
  author = {{Dayeon Kang} and {Hyejun Jeong} and {Jade Sheffey} and {Pubali Datta} and {Amir Houmansadr}},
  year = {2026},
  eprint = {2606.20910v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.20910v1},
  note = {First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T20:07:39Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.30119", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.30119"}}
@misc{arxiv_2606_30119,
  title = {{On the Internet, Nobody Knows You're an LLM Bot: Unmasking Web Agents with Multi-Layer Fingerprinting}},
  author = {{Iliana Fayolle} and {Sihem Bouhenniche} and {Samuel Pélissier} and {Pierre Laperdrix} and {Clémentine Maurice} and {Walter Rudametkin}},
  year = {2026},
  eprint = {2606.30119v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.30119v1},
  note = {First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T10:51:13Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.06118", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.06118"}}
@misc{arxiv_2607_06118,
  title = {{WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation}},
  author = {{Wei Dong} and {Tianyu Fu} and {Zhe Yu} and {Hanning Wang} and {Anyang Su} and {Zhizhou Fang} and {Yuyang Chen} and {Shuo Wang} and {Minghui Wu} and {Ping Jiang} and {Zhen Lei} and {Chenxu Zhao}},
  year = {2026},
  eprint = {2607.06118v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.06118v1},
  note = {First published: 2026-07-07; Recorded arXiv version: v1; Recorded version updated: 2026-07-07T10:27:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.14443", "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:2607.15193", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.15193"}}
@misc{arxiv_2607_15193,
  title = {{Plover: Steering GUI Agents through Plan-Centric Interaction}},
  author = {{Madhumitha Venkatesan} and {Shicheng Wen} and {Jiajing Guo} and {Jorge Piazentin Ono} and {Liu Ren} and {Dongyu Liu}},
  year = {2026},
  eprint = {2607.15193v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.15193v1},
  note = {First published: 2026-07-16; Recorded arXiv version: v1; Recorded version updated: 2026-07-16T16:48:39Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.17527", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.17527"}}
@misc{arxiv_2607_17527,
  title = {{Sidekick: Designing Communication for Effective Multitasking with Computer Use Agents}},
  author = {{Ruei-Che Chang} and {Wenqian Xu} and {Dingzeyu Li} and {Bryan Wang} and {Anhong Guo}},
  year = {2026},
  eprint = {2607.17527v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.17527v1},
  note = {First published: 2026-07-20; Recorded arXiv version: v1; Recorded version updated: 2026-07-20T04:03:38Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.28367", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28367"}}
@misc{arxiv_2607_28367,
  title = {{How Benchmarks Mis-Score Computer-Use Agents}},
  author = {{Zihan Dong} and {Zhiyuan Ma} and {Zekun Wang} and {Yunqing Li} and {Zirou Liu} and {Ruixuan Deng} and {Qishi Zhan} and {Rui Qian}},
  year = {2026},
  eprint = {2607.28367v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.28367v1},
  note = {First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T15:29:42Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2608.27808", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.27808"}}
@misc{arxiv_2608_27808,
  title = {{CURA: Certified Runtime Alarms for Computer-Use Agents}},
  author = {{Divake Kumar} and {Sina Tayebati} and {Devashri Naik} and {Amanda Sofie Rios} and {Nilesh Ahuja} and {Omesh Tickoo} and {Ranganath Krishnan} and {Amit Ranjan Trivedi}},
  year = {2026},
  eprint = {2608.27808v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.27808v1},
  note = {First published: 2026-08-28; Recorded arXiv version: v1; Recorded version updated: 2026-08-28T00:50:47Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.02057", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02057"}}
@misc{arxiv_2609_02057,
  title = {{Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision}},
  author = {{Sitong Pan} and {Yipeng Shen} and {Yilin Lu} and {Caiwen Ding} and {Lu Cheng} and {Qianwen Wang}},
  year = {2026},
  eprint = {2609.02057v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02057v1},
  note = {First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T03:34:47Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.24890", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.24890"}}
@misc{arxiv_2609_24890,
  title = {{OSWorld-Pro: Process-based Evaluation for Computer Use Agents}},
  author = {{Zhilin Wang} and {Shaokun Zhang} and {Yifan Zhang} and {Hao Zhang} and {Jin Xu} and {Binfeng Xu} and {Jian Hu} and {Yunheng Zou} and {Karan Sapra} and {Andrew Tao} and {Jan Kautz} and {Yi Dong}},
  year = {2026},
  eprint = {2609.24890v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.24890v1},
  note = {First published: 2026-09-21; Recorded arXiv version: v1; Recorded version updated: 2026-09-21T16:55:24Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.34113", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.34113"}}
@misc{arxiv_2609_34113,
  title = {{GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions}},
  author = {{Shaoqing Zhang} and {Kehai Chen} and {Xuefeng Bai} and {Zhuosheng Zhang} and {Pengfei Zhang} and {Yang Xiang} and {Min Zhang}},
  year = {2026},
  eprint = {2609.34113v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34113v2},
  note = {First published: 2026-09-28; Recorded arXiv version: v2; Recorded version updated: 2026-09-29T09:05:42Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.37176", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.37176"}}
@misc{arxiv_2609_37176,
  title = {{Absorbed in Inertia: Activation Analysis for Computer-Use Agents}},
  author = {{Giulio Segalini} and {Zhi Wen Soi} and {Jérémie Decouchant} and {Lydia Chen}},
  year = {2026},
  eprint = {2609.37176v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.37176v1},
  note = {First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T10:01:52Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.00948", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.00948"}}
@misc{arxiv_2610_00948,
  title = {{GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution}},
  author = {{Geyi Yang} and {Zikun Qu} and {Xiang Li} and {Zhiyong Wang} and {Min Zhang} and {Shipei Zeng} and {Zhongxiang Dai}},
  year = {2026},
  eprint = {2610.00948v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.00948v1},
  note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T02:31:20Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.01491", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.01491"}}
@misc{arxiv_2610_01491,
  title = {{Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories}},
  author = {{Chengguang Gan} and {Zimeng He} and {Yoshihiro Tsujii} and {Ken-ichiro Kobayashi} and {Hiroki Itoh} and {Kotaro Funakoshi}},
  year = {2026},
  eprint = {2610.01491v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.01491v1},
  note = {First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T11:31:37Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.03036", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.03036"}}
@misc{arxiv_2610_03036,
  title = {{WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites}},
  author = {{Jiangang Han}},
  year = {2026},
  eprint = {2610.03036v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.03036v2},
  note = {First published: 2026-10-02; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T13:46:51Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.09944", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.09944"}}
@misc{arxiv_2610_09944,
  title = {{AgentTime: Can Agents Estimate and Control Their Own Runtime?}},
  author = {{Michael Ofengenden} and {Maksym Andriushchenko}},
  year = {2026},
  eprint = {2610.09944v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.09944v2},
  note = {First published: 2026-10-07; Recorded arXiv version: v2; Recorded version updated: 2026-10-08T09:06:36Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.15502", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.15502"}}
@misc{arxiv_2610_15502,
  title = {{From Observations to Authorized Actions: Measuring Source Information in Android Agents}},
  author = {{Hyobin Ahn} and {Dongjae Lee}},
  year = {2026},
  eprint = {2610.15502v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.15502v1},
  note = {First published: 2026-10-11; Recorded arXiv version: v1; Recorded version updated: 2026-10-11T10:09:44Z.}
}

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

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

% AwesomeCUA: {"catalog_id": "arxiv:2610.26703", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26703"}}
@misc{arxiv_2610_26703,
  title = {{Comparing Computer Use Behavior Across Multiple Levels of Abstraction}},
  author = {{Ananya Gubbi Mohanbabu} and {Rosiana Natalie} and {Anhong Guo} and {Amy Pavel}},
  year = {2026},
  eprint = {2610.26703v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.26703v1},
  note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T16:39:11Z.}
}