% AwesomeCUA: {"catalog_id": "arxiv:2404.06474", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2404.06474"}}
@misc{arxiv_2404_06474,
  title = {{Autonomous Evaluation and Refinement of Digital Agents}},
  author = {{Jiayi Pan} and {Yichi Zhang} and {Nicholas Tomlin} and {Yifei Zhou} and {Sergey Levine} and {Alane Suhr}},
  year = {2024},
  eprint = {2404.06474v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.06474v3},
  note = {First published: 2024-04-09; Recorded arXiv version: v3; Recorded version updated: 2024-10-07T14:19:37Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2411.03817", "catalog_review_status": "curated", "catalog_scope": "adjacent", "identifiers": {"arxiv": "2411.03817"}}
@misc{arxiv_2411_03817,
  title = {{From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning}},
  author = {{Zhirui Deng} and {Zhicheng Dou} and {Yutao Zhu} and {Ji-Rong Wen} and {Ruibin Xiong} and {Mang Wang} and {Weipeng Chen}},
  year = {2024},
  eprint = {2411.03817v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.03817v3},
  note = {First published: 2024-11-06; Recorded arXiv version: v3; Recorded version updated: 2024-12-09T09:20:11Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv: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:2507.14293", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2507.14293"}}
@misc{arxiv_2507_14293,
  title = {{WebGuard: Building a Generalizable Guardrail for Web Agents}},
  author = {{Boyuan Zheng} and {Zeyi Liao} and {Scott Salisbury} and {Zeyuan Liu} and {Michael Lin} and {Qinyuan Zheng} and {Zifan Wang} and {Xiang Deng} and {Dawn Song} and {Huan Sun} and {Yu Su}},
  year = {2025},
  eprint = {2507.14293v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.14293v1},
  note = {First published: 2025-07-18; Recorded arXiv version: v1; Recorded version updated: 2025-07-18T18:06:27Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2507.15846", "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:2508.11360", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2508.11360"}}
@misc{arxiv_2508_11360,
  title = {{CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks}},
  author = {{Songqin Nong} and {Xiaoxuan Tang} and {Jingxuan Xu} and {Sheng Zhou} and {Jianfeng Chen} and {Tao Jiang} and {Wenhao Xu}},
  year = {2025},
  eprint = {2508.11360v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.11360v2},
  note = {First published: 2025-08-15; Recorded arXiv version: v2; Recorded version updated: 2026-03-13T11:10:50Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.14172", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.14172"}}
@misc{arxiv_2509_14172,
  title = {{TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning}},
  author = {{Ziyuan Chen} and {Zhenghui Zhao} and {Zhangye Han} and {Miancan Liu} and {Xianhang Ye} and {Yiqing Li} and {Hongbo Min} and {Jinkui Ren} and {Xiantao Zhang} and {Guitao Cao}},
  year = {2025},
  eprint = {2509.14172v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.14172v2},
  note = {First published: 2025-09-17; Recorded arXiv version: v2; Recorded version updated: 2025-09-19T02:13:09Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.17917", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.17917"}}
@misc{arxiv_2509_17917,
  title = {{Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent}},
  author = {{Junyu Lu} and {Songxin Zhang} and {Zejian Xie} and {Zhuoyang Song} and {Jiaxing Zhang}},
  year = {2025},
  eprint = {2509.17917v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.17917v1},
  note = {First published: 2025-09-22; Recorded arXiv version: v1; Recorded version updated: 2025-09-22T15:40:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.21823", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.21823"}}
@misc{arxiv_2509_21823,
  title = {{ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration}},
  author = {{Gaole Dai} and {Shiqi Jiang} and {Ting Cao} and {Yuqing Yang} and {Yuanchun Li} and {Rui Tan} and {Mo Li} and {Lili Qiu}},
  year = {2025},
  eprint = {2509.21823v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.21823v2},
  note = {First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-04-15T09:19:46Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2509.23263", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2509.23263"}}
@misc{arxiv_2509_23263,
  title = {{GUI-PRA: Process Reward Agent for GUI Tasks}},
  author = {{Tao Xiong} and {Xavier Hu} and {Yurun Chen} and {Yuhang Liu} and {Changqiao Wu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Shengyu Zhang}},
  year = {2025},
  eprint = {2509.23263v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.23263v3},
  note = {First published: 2025-09-27; Recorded arXiv version: v3; Recorded version updated: 2026-08-30T18:12:14Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2510.02250", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2510.02250"}}
@misc{arxiv_2510_02250,
  title = {{Scaling Agents for Computer Use}},
  author = {{Gonzalo Gonzalez-Pumariega} and {Vincent Tu} and {Chih-Lun Lee} and {Jiachen Yang} and {Ang Li} and {Xin Eric Wang}},
  year = {2025},
  eprint = {2510.02250v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.02250v2},
  note = {First published: 2025-10-02; Recorded arXiv version: v2; Recorded version updated: 2026-02-03T23:48:45Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2512.10962", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.10962"}}
@misc{arxiv_2512_10962,
  title = {{WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering}},
  author = {{Yifei He} and {Pranit Chawla} and {Yaser Souri} and {Subhojit Som} and {Xia Song}},
  year = {2025},
  eprint = {2512.10962v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.10962v3},
  note = {First published: 2025-11-22; Recorded arXiv version: v3; Recorded version updated: 2026-02-04T19:36:03Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2512.15431", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.15431"}}
@misc{arxiv_2512_15431,
  title = {{Step-GUI Technical Report}},
  author = {{Haolong Yan} and {Jia Wang} and {Xin Huang} and {Yeqing Shen} and {Ziyang Meng} and {Zhimin Fan} and {Kaijun Tan} and {Jin Gao} and {Lieyu Shi} and {Mi Yang} and {Shiliang Yang} and {Zhirui Wang} and {Brian Li} and {Kang An} and {Chenyang Li} and {Lei Lei} and {Mengmeng Duan} and {Danxun Liang} and {Guodong Liu} and {Hang Cheng} and {Hao Wu} and {Jie Dong} and {Junhao Huang} and {Mei Chen} and {Renjie Yu} and {Shunshan Li} and {Xu Zhou} and {Yiting Dai} and {Yineng Deng} and {Yingdan Liang} and {Zelin Chen} and {Wen Sun} and {Chengxu Yan} and {Chunqin Xu} and {Dong Li} and {Fengqiong Xiao} and {Guanghao Fan} and {Guopeng Li} and {Guozhen Peng} and {Hongbing Li} and {Hang Li} and {Hongming Chen} and {Jingjing Xie} and {Jianyong Li} and {Jingyang Zhang} and {Jiaju Ren} and {Jiayu Yuan} and {Jianpeng Yin} and {Kai Cao} and {Liang Zhao} and {Liguo Tan} and {Liying Shi} and {Mengqiang Ren} and {Min Xu} and {Manjiao Liu} and {Mao Luo} and {Mingxin Wan} and {Na Wang} and {Nan Wu} and {Ning Wang} and {Peiyao Ma} and {Qingzhou Zhang} and {Qiao Wang} and {Qinlin Zeng} and {Qiong Gao} and {Qiongyao Li} and {Shangwu Zhong} and {Shuli Gao} and {Shaofan Liu} and {Shisi Gao} and {Shuang Luo} and {Xingbin Liu} and {Xiaojia Liu} and {Xiaojie Hou} and {Xin Liu} and {Xuanti Feng} and {Xuedan Cai} and {Xuan Wen} and {Xianwei Zhu} and {Xin Liang} and {Xin Liu} and {Xin Zhou} and {Yifan Sui} and {Yingxiu Zhao} and {Yukang Shi} and {Yunfang Xu} and {Yuqing Zeng} and {Yixun Zhang} and {Zejia Weng} and {Zhonghao Yan} and {Zhiguo Huang} and {Zhuoyu Wang} and {Zihan Yan} and {Zheng Ge} and {Jing Li} and {Yibo Zhu} and {Binxing Jiao} and {Xiangyu Zhang} and {Daxin Jiang}},
  year = {2025},
  eprint = {2512.15431v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.15431v2},
  note = {First published: 2025-12-17; Recorded arXiv version: v2; Recorded version updated: 2025-12-19T17:36:21Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2512.16295", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.16295"}}
@misc{arxiv_2512_16295,
  title = {{OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models}},
  author = {{Zhenyu Wu} and {Jingjing Xie} and {Zehao Li} and {Bowen Yang} and {Qiushi Sun} and {Zhaoyang Liu} and {Zhoumianze Liu} and {Yu Qiao} and {Xiangyu Yue} and {Zun Wang} and {Zichen Ding}},
  year = {2025},
  eprint = {2512.16295v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.16295v1},
  note = {First published: 2025-12-18; Recorded arXiv version: v1; Recorded version updated: 2025-12-18T08:29:50Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2512.19396", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2512.19396"}}
@misc{arxiv_2512_19396,
  title = {{EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration}},
  author = {{Runze Li} and {Yuwen Zhai} and {Bo Xu} and {LiWu Xu} and {Nian Shi} and {Wei Zhang} and {Ran Lin} and {Liang Wang}},
  year = {2025},
  eprint = {2512.19396v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.19396v3},
  note = {First published: 2025-12-22; Recorded arXiv version: v3; Recorded version updated: 2026-04-10T06:20:00Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2601.13060", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.13060"}}
@misc{arxiv_2601_13060,
  title = {{MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux}},
  author = {{Zecheng Li} and {Zhihui Cao} and {Wenke Huang} and {Yudong Zhang} and {Keying Qi} and {Rui Wang} and {Zeyu Zheng} and {Jian Zhao} and {Hao Zhu} and {Hengxin Wu} and {Yuran Wang} and {Guitao Fan} and {Guokun Wu} and {Yicong Liu} and {Zhilin Gao} and {Haikun Xu} and {He Yang} and {Minqi Xiang} and {Xingyu Liu} and {Zuojian Wang}},
  year = {2026},
  eprint = {2601.13060v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.13060v1},
  note = {First published: 2026-01-19; Recorded arXiv version: v1; Recorded version updated: 2026-01-19T13:50:43Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2601.18197", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.18197"}}
@misc{arxiv_2601_18197,
  title = {{GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models}},
  author = {{Shaokang Wang} and {Pei Fu} and {Ruoceng Zhang} and {Shaojie Zhang} and {Xiuwen Xi} and {Jiahui Yang} and {Bin Qin} and {Ying Huang} and {Zhenbo Luo} and {Jian Luan}},
  year = {2026},
  eprint = {2601.18197v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.18197v2},
  note = {First published: 2026-01-26; Recorded arXiv version: v2; Recorded version updated: 2026-06-26T07:19:55Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2601.21872", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2601.21872"}}
@misc{arxiv_2601_21872,
  title = {{WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents}},
  author = {{Yao Zhang} and {Shijie Tang} and {Zeyu Li} and {Zhen Han} and {Volker Tresp}},
  year = {2026},
  eprint = {2601.21872v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.21872v2},
  note = {First published: 2026-01-29; Recorded arXiv version: v2; Recorded version updated: 2026-04-09T17:48:11Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2602.00575", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.00575"}}
@misc{arxiv_2602_00575,
  title = {{Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction}},
  author = {{Chaoqun Cui} and {Jing Huang} and {Shijing Wang} and {Liming Zheng} and {Qingchao Kong} and {Zhixiong Zeng}},
  year = {2026},
  eprint = {2602.00575v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.00575v2},
  note = {First published: 2026-01-31; Recorded arXiv version: v2; Recorded version updated: 2026-07-25T06:54:35Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2602.10356", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.10356"}}
@misc{arxiv_2602_10356,
  title = {{Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents}},
  author = {{Tianci Xue} and {Zeyi Liao} and {Tianneng Shi} and {Zilu Wang} and {Kai Zhang} and {Dawn Song} and {Yu Su} and {Huan Sun}},
  year = {2026},
  eprint = {2602.10356v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.10356v2},
  note = {First published: 2026-02-10; Recorded arXiv version: v2; Recorded version updated: 2026-05-11T00:11:46Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2602.11524", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2602.11524"}}
@misc{arxiv_2602_11524,
  title = {{Adaptive Milestone Reward for GUI Agents}},
  author = {{Congmin Zheng} and {Xiaoyun Mo} and {Xinbei Ma} and {Qiqiang Lin} and {Yin Zhao} and {Jiachen Zhu} and {Xingyu Lou} and {Jun Wang} and {Zhaoxiang Wang} and {Weiwen Liu} and {Zhuosheng Zhang} and {Yong Yu} and {Weinan Zhang}},
  year = {2026},
  eprint = {2602.11524v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.11524v1},
  note = {First published: 2026-02-12; Recorded arXiv version: v1; Recorded version updated: 2026-02-12T03:31:40Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2602.13653", "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: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:2603.19191", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.19191"}}
@misc{arxiv_2603_19191,
  title = {{OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards}},
  author = {{Zehao Li} and {Zhenyu Wu} and {Yibo Zhao} and {Bowen Yang} and {Jingjing Xie} and {Zhaoyang Liu} and {Zhoumianze Liu} and {Kaiming Jin} and {Jianze Liang} and {Zonglin Li} and {Feng Wu} and {Bowen Zhou} and {Zun Wang} and {Zichen Ding}},
  year = {2026},
  eprint = {2603.19191v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.19191v1},
  note = {First published: 2026-03-19; Recorded arXiv version: v1; Recorded version updated: 2026-03-19T17:47:47Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2603.19685", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2603.19685"}}
@misc{arxiv_2603_19685,
  title = {{A Subgoal-driven Framework for Improving Long-Horizon LLM Agents}},
  author = {{Taiyi Wang} and {Sian Gooding} and {Florian Hartmann} and {Oriana Riva} and {Edward Grefenstette}},
  year = {2026},
  eprint = {2603.19685v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.19685v1},
  note = {First published: 2026-03-20; Recorded arXiv version: v1; Recorded version updated: 2026-03-20T06:32:16Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.05157", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.05157"}}
@misc{arxiv_2604_05157,
  title = {{IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents}},
  author = {{Rongqian Chen} and {Yu Li} and {Zeyu Fang} and {Sizhe Tang} and {Weidong Cao} and {Tian Lan}},
  year = {2026},
  eprint = {2604.05157v3},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.05157v3},
  note = {First published: 2026-04-06; Recorded arXiv version: v3; Recorded version updated: 2026-05-28T08:13:55Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.06240", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.06240"}}
@misc{arxiv_2604_06240,
  title = {{The Art of Building Verifiers for Computer Use Agents}},
  author = {{Corby Rosset} and {Pratyusha Sharma} and {Andrew Zhao} and {Miguel Gonzalez-Fernandez} and {Ahmed Awadallah}},
  year = {2026},
  eprint = {2604.06240v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.06240v1},
  note = {First published: 2026-04-05; Recorded arXiv version: v1; Recorded version updated: 2026-04-05T06:26:05Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.07277", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.07277"}}
@misc{arxiv_2604_07277,
  title = {{Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions}},
  author = {{Guo Gan} and {Yuxuan Ding} and {Cong Chen} and {Yuwei Ren} and {Yin Huang} and {Hong Zhou}},
  year = {2026},
  eprint = {2604.07277v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.07277v2},
  note = {First published: 2026-04-08; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T03:06:31Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2604.18240", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2604.18240"}}
@misc{arxiv_2604_18240,
  title = {{AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation}},
  author = {{Wentao Shi} and {Yu Wang} and {Yuyang Zhao} and {Yuxin Chen} and {Fuli Feng} and {Xueyuan Hao} and {Xi Su} and {Qi Gu} and {Hui Su} and {Xunliang Cai} and {Xiangnan He}},
  year = {2026},
  eprint = {2604.18240v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.18240v1},
  note = {First published: 2026-04-20; Recorded arXiv version: v1; Recorded version updated: 2026-04-20T13:23:38Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.07027", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.07027"}}
@misc{arxiv_2606_07027,
  title = {{StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents}},
  author = {{Haojie Hao} and {Longkun Hao} and {Yihang Lou} and {Yan Bai} and {Zhenyang Li} and {Zhichao Yang} and {Dongshuo Huang} and {Hongyu Lin} and {Lanqing Hong} and {Jiakai Wang} and {Xianglong Liu}},
  year = {2026},
  eprint = {2606.07027v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.07027v2},
  note = {First published: 2026-06-05; Recorded arXiv version: v2; Recorded version updated: 2026-06-12T07:28:19Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.11078", "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:2606.24515", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.24515"}}
@misc{arxiv_2606_24515,
  title = {{Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation}},
  author = {{Marta Sumyk} and {Oleksandr Kosovan}},
  year = {2026},
  eprint = {2606.24515v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.24515v1},
  note = {First published: 2026-06-23; Recorded arXiv version: v1; Recorded version updated: 2026-06-23T12:46:29Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2606.24525", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2606.24525"}}
@misc{arxiv_2606_24525,
  title = {{VisCritic: Visual State Comparison as Process Reward for GUI Agents}},
  author = {{Jiachen Qian}},
  year = {2026},
  eprint = {2606.24525v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.24525v1},
  note = {First published: 2026-06-23; Recorded arXiv version: v1; Recorded version updated: 2026-06-23T12:57:02Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.23263", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.23263"}}
@misc{arxiv_2607_23263,
  title = {{SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents}},
  author = {{Yang Wan} and {Zhenhao Zhang} and {Jierui Wang} and {Xiangxin Zhou} and {Linchao Zhu}},
  year = {2026},
  eprint = {2607.23263v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.23263v2},
  note = {First published: 2026-07-25; Recorded arXiv version: v2; Recorded version updated: 2026-09-26T12:15:44Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.25904", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.25904"}}
@misc{arxiv_2607_25904,
  title = {{Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification}},
  author = {{Chenrui Shi} and {Yuwei Wu} and {Yang Liu} and {Ruining Feng} and {Zirui Shang} and {Zhi Gao} and {Lifeng Fan} and {Che Sun}},
  year = {2026},
  eprint = {2607.25904v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.25904v2},
  note = {First published: 2026-07-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-29T05:13:57Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2607.28609", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2607.28609"}}
@misc{arxiv_2607_28609,
  title = {{OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models}},
  author = {{Qiushi Sun} and {Kanzhi Cheng} and {Yian Wang} and {Bowen Yang} and {Hang Yan} and {Liheng Chen} and {Fangzhi Xu} and {Zichen Ding} and {Nuo Chen} and {Jialin Cao} and {Xingdong Gong} and {Zehao Li} and {Kaiming Jin} and {Xinfeng Yuan} and {Zhoumianze Liu} and {Jingyang Gong} and {Zhangyue Yin} and {Jiahui Gao} and {Zhiyong Wu} and {Tianbao Xie} and {Jianbing Zhang} and {Ben Kao} and {Lingpeng Kong}},
  year = {2026},
  eprint = {2607.28609v2},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.28609v2},
  note = {First published: 2026-07-30; Recorded arXiv version: v2; Recorded version updated: 2026-08-06T17:55:59Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2608.05587", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.05587"}}
@misc{arxiv_2608_05587,
  title = {{StepReflect: Structured UI Transition Reflection for Mobile GUI Agents}},
  author = {{Linqiang Guo} and {Wei Liu} and {Li Gu} and {Yang Wang} and {Tse-Hsun} and {Chen}},
  year = {2026},
  eprint = {2608.05587v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.05587v1},
  note = {First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T04:17:27Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2608.11434", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.11434"}}
@misc{arxiv_2608_11434,
  title = {{Benchmarking LLM Judges for Mobile Agent Evaluation}},
  author = {{Ziqiang Wang} and {Li Gu} and {Zhixiang Chi} and {Zhi Liu} and {Seyed Mehdi Ayyoubzadeh} and {Yuanhao Yu} and {Yang Wang}},
  year = {2026},
  eprint = {2608.11434v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.11434v1},
  note = {First published: 2026-08-11; Recorded arXiv version: v1; Recorded version updated: 2026-08-11T21:00:46Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2608.22847", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.22847"}}
@misc{arxiv_2608_22847,
  title = {{GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis}},
  author = {{Long Zhang} and {Yuhan Chen} and {Chaoran Zhang} and {Wanxia Cao} and {Kun Huang} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Chenliang Li} and {Lixin Zou}},
  year = {2026},
  eprint = {2608.22847v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.22847v1},
  note = {First published: 2026-08-24; Recorded arXiv version: v1; Recorded version updated: 2026-08-24T06:27:47Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2608.24174", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2608.24174"}}
@misc{arxiv_2608_24174,
  title = {{Task-Adaptive Rubrics for GUI Reward Modeling}},
  author = {{Tao Xiong} and {Xavier Hu} and {Wenkai Wang} and {Qinzhuo Wu} and {Changqiao Wu} and {Pengzhi Gao} and {Wei Liu} and {Jian Luan} and {Shengyu Zhang}},
  year = {2026},
  eprint = {2608.24174v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.24174v1},
  note = {First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T07:40:12Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.02885", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.02885"}}
@misc{arxiv_2609_02885,
  title = {{Discriminative World Models for Web Agents}},
  author = {{Kelvin Li} and {Dhruv Pendharkar} and {Anish Pahilajani} and {Chuyi Shang} and {Leon Oks} and {Leonid Karlinsky} and {Rogerio Feris} and {Trevor Darrell} and {Roei Herzig}},
  year = {2026},
  eprint = {2609.02885v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02885v1},
  note = {First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T17:59:40Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2609.32351", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2609.32351"}}
@misc{arxiv_2609_32351,
  title = {{From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs}},
  author = {{Yangzhe Peng} and {Xiaoyang Wang} and {Yiyang Zhao} and {Lijun Wu} and {Kun He}},
  year = {2026},
  eprint = {2609.32351v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.32351v1},
  note = {First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T08:14:50Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.18067", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.18067"}}
@misc{arxiv_2610_18067,
  title = {{WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution}},
  author = {{Hang He} and {Linting Wang} and {Guanming Liu} and {Bo Mao} and {Jinxiu Liu} and {Yiran Suo} and {Maosen Zhou} and {Zhiheng Xi} and {Guanting Dong} and {Zhou Shao} and {Rui Zheng} and {Jie Zhou} and {Chengcheng Wan} and {Tao Gui} and {Qi Zhang} and {Xipeng Qiu} and {Xuanjing Huang}},
  year = {2026},
  eprint = {2610.18067v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.18067v1},
  note = {First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T09:52:02Z.}
}

% AwesomeCUA: {"catalog_id": "arxiv:2610.26469", "catalog_review_status": "curated", "catalog_scope": "core", "identifiers": {"arxiv": "2610.26469"}}
@misc{arxiv_2610_26469,
  title = {{VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards}},
  author = {{Zhizhou Wang} and {Yaxi Lu} and {Zhong Zhang} and {Zikun Hu} and {Xin Cong} and {Yankai Lin} and {Fangming Liu}},
  year = {2026},
  eprint = {2610.26469v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.26469v1},
  note = {First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T14:17:33Z.}
}