Elamur Research⌕
☰
home / papers / 2026 / Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions

Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions

Paper · 2026 · Guo Gan, Yuxuan Ding, Cong Chen et al.

Summary

The paper addresses the high cost of online reinforcement learning for Android GUI agents. Emulator interaction (initialization, recovery, reacting to actions) dominates rollout time, and standard methods such as PPO and GRPO extract only one action per expensive state. The authors label this one-action-per-state approach as Single State Single Action (SSSA). Their framework, ANDROID COACH, adopts a Single State Multiple Actions (SSMA) approach instead. For each state reached online, the policy samples several candidate actions. A critic (a Q-function) scores these actions, so they never need to be executed in the emulator.

The critic is kept reliable in three ways:

  • it is updated continually on fresh rollout data;
  • it is supervised by both outcome rewards and a pretrained process reward model (PRM);
  • it is pretrained before RL.

Advantages are computed with ACLOO, which uses the leave-one-out average Q-value of the sampled group as a baseline, so no separate state-value model is needed.

Starting from UI-TARS-1.5-7B, the method improves success rates on AndroidLab and AndroidWorld and trains more efficiently than SSSA baselines. This matters because it makes online agent training cheaper.

Key points

  • Main results: success rate rises by 7.5% on AndroidLab and 8.3% on AndroidWorld over UI-TARS-1.5-7B. Training efficiency is about 1.4× that of PPO and GRPO at equal success rates.
  • Why emulators are the bottleneck: environment-side time is roughly 1.7× the time spent loading the model and running inference.
  • Number of sampled actions N (without PRM): AndroidLab success rate climbs from 34.8% at N=1 to 37.0% at N=4. Gains flatten at N=8. Training time grows sub-linearly: 1.62× at N=4 and 2.18× at N=8.
  • Effect of the PRM: success rate improves on AndroidLab (39.4% vs 37.0%) and AndroidWorld (41.1% vs 39.1%). The reasonable operation ratio (ROR) rises by 6.6 and 5.1 points. Removing the ACLOO baseline lowers the success rate to 36.0%.
  • Limitations: outcome rewards depend on a GPT-4o verifier that sometimes hallucinates. The study includes no SFT stage and no system-level parallelization.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Zhejiang UniversityHangzhou · China172 works · 12,988 citations🏢QualcommSan Diego · United States6 works · 144 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksSoftware · 92 works

Cite

Cite as Guo Gan, Yuxuan Ding, Cong Chen, Yuwei Ren, Yin Huang and Hong Zhou. 2026. Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.613

@inproceedings{gan2026android,
  title = {{Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions}},
  author = {Guo Gan, Yuxuan Ding, Cong Chen, Yuwei Ren, Yin Huang and Hong Zhou},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.613},
  url = {https://doi.org/10.18653/v1/2026.acl-long.613}
}

References

68 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, and Sara Hooker. 2024. Back to basics: Revisiting REINFORCE-style optimization for learning from human feedback in LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Compu… find
  2. Anthropic. 2025. Introducing claude 4. find
  3. Hao Bai, Yifei Zhou, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, and Aviral Kumar. 2024. Digirl: Training in-the-wild device-control agents with autonomous reinforcement learning. In Advances in Neural Information Processing Systems, volume 37, pages 12461–12495. Curran Associates, Inc. find
  4. Hao Bai, Yifei Zhou, Li Li, Sergey Levine, and Aviral Kumar. 2025a. Digi-q: Learning vlm q-value functions for training device-control agents. In International Conference on Representation Learning, volume 2025, pages 33183–33203. find
  5. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025b. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  6. Cong Chen, Kaixiang Ji, Hao Zhong, Muzhi Zhu, Anzhou Li, Guo Gan, Ziyuan Huang, Cheng Zou, Jiajia Liu, Jingdong Chen, Hao Chen, and Chunhua Shen. 2025a. Gui-shepherd: Reliable process reward and verification for long-sequence gui tasks. find
  7. Cong Chen, Mingyu Liu, Chenchen Jing, Yizhou Zhou, Fengyun Rao, Hao Chen, Bo Zhang, and Chunhua Shen. 2025b. Perturbollava: Reducing multimodal hallucinations with perturbative visual training. arXiv preprint arXiv:2503.06486. — [arXiv:2503.06486](https://arxiv.org/abs/2503.06486) find
  8. Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, and Wei Zhang. 2026. A survey of inductive reasoning for large language models. Preprint, arXiv:2510.10182.
  9. Petros Christodoulou. 2019. for discrete action settings. arXiv:1910.07207. — [arXiv:1910.07207](https://arxiv.org/abs/1910.07207) find
  10. Soft actor-critic arXiv preprint Kamil Ciosek and Shimon Whiteson. 2018. Expected policy gradients. arXiv preprint arXiv:1706.05374. — [arXiv:1706.05374](https://arxiv.org/abs/1706.05374) find
  11. Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, and 1 others. 2025. Process reinforcement through implicit rewards. arXiv preprint arXiv:2502.01456.
  12. Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, and Tao Gui. 2026. Octobench: Benchmarking scaffold-aware instruction following in repository-grounded agentic coding. Pr…
  13. Guanting Dong, Hangyu Mao, Kai Ma, Licheng Bao, Yifei Chen, Zhongyuan Wang, Zhongxia Chen, Jiazhen Du, Huiyang Wang, Fuzheng Zhang, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, and Zhicheng Dou. 2025. Agentic reinforced policy optimization. Preprint, arXiv:2507.19849. — [arXiv:2507.19849](https://arxiv.org/abs/2507.19849) find
  14. Wei Fu, Jiaxuan Gao, Xujie Shen, Chen Zhu, Zhiyu Mei, Chuyi He, Shusheng Xu, Guo Wei, Jun Mei, Jiashu Wang, Tongkai Yang, Binhang Yuan, and Yi Wu. 2025. Areal: A large-scale asynchronous reinforcement learning system for language reasoning. Preprint, arXiv:2505.24298. find
  15. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025. Deepseekr1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633–638. find
  16. Physical Intelligence, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachy Groom, and ∗ 37… — [arXiv:2511.14759](https://arxiv.org/abs/2511.14759) find
  17. Vijay Konda and John Tsitsiklis. 1999. Actor-critic algorithms. Advances in neural information processing systems, 12. find
  18. Wouter Kool, Herke van Hoof, and Max Welling. 2019. Buy 4 reinforce samples, get a baseline for free! find
  19. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the 29th Symposium on Operating Systems Principles, SOSP ’23, page 611…
  20. Wei Li, William Bishop, Alice Li, Chris Rawles, Folawiyo Campbell-Ajala, Divya Tyamagundlu, and Oriana Riva. 2024. On the effects of data scale on computer control agents. arXiv preprint arXiv:2406.03679. find
  21. Shuquan Lian, Yuhang Wu, Jia Ma, Yifan Ding, Zihan Song, Bingqi Chen, Xiawu Zheng, and Hui Li. 2025. Ui-agile: Advancing gui agents with effective reinforcement learning and precise inference-time grounding. arXiv preprint arXiv:2507.22025. — [arXiv:2507.22025](https://arxiv.org/abs/2507.22025) find
  22. Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, and Xuanjing Huang. 2026. Mm-doc-r1: Training agents for long document visual question answering through multi-turn reinforcement learnin… find
  23. Ilya Loshchilov and Frank Hutter. 2017. weight decay regularization in adam. abs/1711.05101. find
  24. Fixing CoRR, Fanbin Lu, Zhisheng Zhong, Shu Liu, Chi-Wing Fu, and Jiaya Jia. 2025a. Arpo:end-to-end policy optimization for gui agents with experience replay. find
  25. Quanfeng Lu, Wenqi Shao, Zitao Liu, Lingxiao Du, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, and Ping Luo. 2025b. Guiodyssey: A comprehensive dataset for cross-app gui navigation on mobile devices. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pag… find
  26. Zhengxi Lu, Yuxiang Chai, Yaxuan Guo, Xi Yin, Liang Liu, Hao Wang, Han Xiao, Shuai Ren, Guanjing Xiong, and Hongsheng Li. 2025c. Ui-r1: Enhancing efficient action prediction of gui agents by reinforcement learning. find
  27. Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, and Yueting Zhuang. 2025d. Ui-s1: Advancing gui automation via semi-online reinforcement learning. find
  28. Run Luo, Lu Wang, Wanwei He, Longze Chen, Jiaming Li, and Xiaobo Xia. 2025. Gui-r1 : A generalist r1-style vision-language action model for gui agents. find
  29. Zhihao Luo, Wentao Yan, Jingyu Gong, Min Wang, Zhizhong Zhang, Xuhong Wang, Yuan Xie, and Xin Tan. 2026. Navimaster: Learning a unified policy for gui and embodied navigation tasks. Preprint, arXiv:2508.02046.
  30. Weijian Ma, Ruoxin Chen, Keyue Zhang, Shuang Wu, and Shouhong Ding. 2025. Instruct where the model fails: Generative data augmentation via guided self-contrastive fine-tuning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6):5991– 5999. find
  31. Weijian Ma, Shizhao Sun, Tianyu Yu, Ruiyu Wang, Tat-Seng Chua, and Jiang Bian. 2026. Thinking with blueprints: Assisting vision-language models in spatial reasoning via structured object representation. Preprint, arXiv:2601.01984. — [arXiv:2601.01984](https://arxiv.org/abs/2601.01984) find
  32. OpenAI, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, Alex Nichol, and 400 others. 2024. Gpt-4o sys…
  33. Xue Bin Peng, Aviral Kumar, Grace Zhang, and Sergey Levine. 2019. Advantage-weighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177. find
  34. Yujia Qin, Yining Ye, Junjie Fang, Haoming Wang, Shihao Liang, Shizuo Tian, Junda Zhang, Jiahao Li, Yunxin Li, Shijue Huang, Wanjun Zhong, Kuanye Li, Jiale Yang, Yu Miao, Woyu Lin, Longxiang Liu, Xu Jiang, Qianli Ma, Jingyu Li, and 16 others. 2025. Ui-tars: Pioneering automated gui interaction with…
  35. Changle Qu, Sunhao Dai, Hengyi Cai, Jun Xu, Shuaiqiang Wang, and Dawei Yin. 2026. Matchtir: Fine-grained supervision for tool-integrated reasoning via bipartite matching.
  36. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, 36:53728–53741.
  37. Chris Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair, Alice Li, William Bishop, Wei Li, Folawiyo Campbell-Ajala, Daniel Toyama, Robert Berry, Divya Tyamagundlu, Timothy Lillicrap, and Oriana Riva. 2025. Androidworld: A dynamic benchmarking environment for aut… find
  38. John Schulman, Philipp Moritz, Sergey Levine, Michael I. Jordan, and Pieter Abbeel. 2016. High-dimensional continuous control using generalized advantage estimation. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceed… find
  39. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. find
  40. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. find
  41. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. Preprint, arXiv:2402.03300.
  42. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. Hybridflow: A flexible and efficient rlhf framework. In Proceedings of the Twentieth European Conference on Computer Systems, EuroSys ’25’, page 1279–1297, New York, NY, USA. Asso…
  43. Yucheng Shi, Wenhao Yu, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, and Dong Yu. 2025. Mobilegui-rl: Advancing mobile gui agent through reinforcement learning in online environment. Preprint, arXiv:2507.05720. — [arXiv:2507.05720](https://arxiv.org/abs/2507.05720) find
  44. Jinwei Su, Qizhen Lan, Yinghui Xia, Lifan Sun, Weiyou Tian, Tianyu Shi, Xinyuan Song, Lewei He, and Yang Jingsong. 2026. Difficulty-aware agentic orchestration for query-specific multi-agent workflows. Preprint, arXiv:2509.11079. — [arXiv:2509.11079](https://arxiv.org/abs/2509.11079) find
  45. Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, and Zhiyong Wu. 2025. OS-genesis: Automating GUI agent trajectory construction via reverse task synthesis. In Proceedings of the…
  46. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, Soroosh Mariooryad, Yifan Ding, Xinyang Geng, Fred Alcober, Roy Frostig, Mark Omernick, Lexi Walker, Cosmin Paduraru, Christina Sorokin, and 1118 others. 2024. G… — Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
  47. Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallouédec. 2020. Trl: Transformer reinforcement learning. https://github.com/huggingface/trl. ↗
  48. Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Aoyan Li, Bo Li, Chen Dun, and 93 others. 2025. Ui-tars-2 technical report: Advancing gui age…
  49. Yuyang Wanyan, Xi Zhang, Haiyang Xu, Haowei Liu, Junyang Wang, Jiabo Ye, Yutong Kou, Ming Yan, Fei Huang, Xiaoshan Yang, Weiming Dong, and Changsheng Xu. 2025. Look before you leap: A gui-critic-r1 model for pre-operative error diagnosis in gui automation. find
  50. Christopher John Cornish Hellaby Watkins and 1 others. 1989. Learning from delayed rewards. find
  51. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824– 24837.
  52. Jinbiao Wei, Yilun Zhao, Kangqi Ni, and Arman Cohan. 2026. Anchor: Branch-point data generation for gui agents. arXiv preprint arXiv:2602.07153.
  53. Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, and Lihong Li. 2025. WebAgent-r1: Training web agents via end-to-end multi-turn reinforcement learning. In Proceedings of the 2025 Conference on Empirical Methods in Natural L…
  54. Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, and Jianhua Tao. 2026. Atlas: Orchestrating heterogeneous models and tools for multi-domain complex reasoning. arXiv preprint arXiv:2601.03872.
  55. Han Xiao, Guozhi Wang, Yuxiang Chai, Zimu Lu, Weifeng Lin, Hao He, Lue Fan, Liuyang Bian, Rui Hu, Liang Liu, Shuai Ren, Yafei Wen, Xiaoxin Chen, Aojun Zhou, and Hongsheng Li. 2025. Ui-genie: A self-improving approach for iteratively boosting mllm-based mobile gui agents. find
  56. Bin Xie, Rui Shao, Gongwei Chen, Kaiwen Zhou, Yinchuan Li, Jie Liu, Min Zhang, and Liqiang Nie. 2025. GUI-explorer: Autonomous exploration and mining of transition-aware knowledge for GUI agent. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lon…
  57. Fangzhi Xu, Hang Yan, Qiushi Sun, Jinyang Wu, Zixian Huang, Muye Huang, Jingyang Gong, Zichen Ding, Kanzhi Cheng, Yian Wang, and 1 others. 2026. Odysseyarena: Benchmarking large language models for long-horizon, active and inductive interactions. arXiv preprint arXiv:2602.05843. — [arXiv:2602.05843](https://arxiv.org/abs/2602.05843) find
  58. Yifan Xu, Xiao Liu, Xinghan Liu, Jiaqi Fu, Hanchen Zhang, Bohao Jing, Shudan Zhang, Yuting Wang, Wenyi Zhao, and Yuxiao Dong. 2025a. Mobilerl: Online agentic reinforcement learning for mobile gui agents. find
  59. Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, and Yuxiao Dong. 2025b. AndroidLab: Training and systematic benchmarking of android autonomous agents. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume…
  60. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  61. Jiabo Ye, Xi Zhang, Haiyang Xu, Haowei Liu, Junyang Wang, Zhaoqing Zhu, Ziwei Zheng, Feiyu Gao, Junjie Cao, Zhengxi Lu, Jitong Liao, Qi Zheng, Fei Huang, Jingren Zhou, and Ming Yan. 2025. Mobile-agent-v3: Fundamental agents for gui automation. Preprint, arXiv:2508.15144. — [arXiv:2508.15144](https://arxiv.org/abs/2508.15144) find
  62. Chi Zhang, Zhao Yang, Jiaxuan Liu, Yanda Li, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, and Gang Yu. 2025a. Appagent: Multimodal agents as smartphone users. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, CHI ’25, New York, NY, USA. Association for Computing Machin… find
  63. Yuzhe Zhang, Xianwei Xue, Xingyong Wu, Mengke Chen, Chen Liu, Xinran He, Run Shao, Feiran Liu, Huanmin Xu, Qiutong Pan, and Haiwei Wang. 2026. Don’t act blindly: Robust gui automation via action-effect verification and self-correction. Preprint, arXiv:2604.05477.
  64. Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Jie Xie, Wei Zhou, Wang Xu, Yuanheng Zhang, Zhou Su, Zhongwu Zhai, Xiaoming Liu, Yudong Mei, Jianming Xu, and 6 others. 2025b. AgentCPM-GUI: Building mobile-use agents with reinforcement f… find
  65. Zhuosheng Zhang and Aston Zhang. 2024. You only look at screens: Multimodal chain-of-action agents. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3132–3149, Bangkok, Thailand. Association for Computational Linguistics.
  66. Jiani Zheng, Lu Wang, Fangkai Yang, Chaoyun Zhang, Lingrui Mei, Wenjie Yin, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, and Qi Zhang. 2025. Vem: Environment-free exploration for training gui agent with value environment model. find
  67. Hanzhang Zhou, Xu Zhang, Panrong Tong, Jianan Zhang, Liangyu Chen, Quyu Kong, Chenglin Cai, Chen Liu, Yue Wang, Jingren Zhou, and Steven Hoi. 2025. Mai-ui technical report: Real-world centric foundation gui agents. Preprint, arXiv:2512.22047. — [arXiv:2512.22047](https://arxiv.org/abs/2512.22047) find
  68. Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, and Aviral Kumar. 2024. Archer: training language model agents via hierarchical multi-turn rl. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/gan-2026-android-coach-improve-online-agentic/