---
title: "TVWorld: Foundations for Remote-Control TV Agents (2026)"
description: "The authors therefore propose a two-stage Topology-Aware Training scheme, with supervised fine-tuning followed by… 72 references."
authors: ["Zhantao Ma", "Quanfeng Lu", "Shuai Zhong", "Dahai Yu", "Ping Luo", "Michael Ng"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1792/"
doi: "10.18653/v1/2026.findings-acl.1792"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ma-2026-tvworld-foundations-remote-control-tv/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ma-2026-tvworld-foundations-remote-control-tv/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/54/) / TVWorld: Foundations for Remote-Control TV Agents

# TVWorld: Foundations for Remote-Control TV Agents

**Authors:** Zhantao Ma, Quanfeng Lu, Shuai Zhong, Dahai Yu, [Ping Luo](https://md.research.elamur.ai/free/en/authors/ping-luo/) and Michael Ng · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1792/) · [PDF](https://aclanthology.org/2026.findings-acl.1792.pdf) · [DOI 10.18653/v1/2026.findings-acl.1792](https://doi.org/10.18653/v1/2026.findings-acl.1792) · [OpenAlex](https://openalex.org/W7166806430)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Most work on LVLM agents for device control assumes pointer or touch input. Smart TVs work differently: the user presses remote keys to move a highlight between elements, and only the highlighted item can be activated. To study this setting, the authors built TVWorld. They crawled real TV interfaces with automated key presses and recorded them as offline navigation graphs, where each node is a UI state and each edge is a key-triggered transition. This makes evaluation reproducible, fast and free of live devices.

From these graphs they derived two benchmarks. TVWorld-N tests multi-step navigation, and TVWorld-G tests locating the focused element. Existing agents do poorly on them, mainly because they lack awareness of the UI's transition structure. The authors therefore propose a two-stage Topology-Aware Training scheme, with supervised fine-tuning followed by reinforcement learning. They use it to train TVTheseus, which surpasses strong closed-source systems on an unseen TV platform. The work provides the first systematic resources for agents that operate TVs by remote control.

## Key points
- Graph data was collected from physical TVs over ADB, a capture card and a serial remote interface. TCL TV interfaces are used for training, and Google TV is held out entirely for out-of-domain evaluation. The action space has 9 options: four directional moves (UP, DOWN, LEFT, RIGHT) plus OK, EXIT, HOME, SETTING and FINISH.
- TVTheseus is built on Qwen3-VL-8B-Instruct. On TVWorld-N, its success rate rises from 20.0 to 68.3, beating Gemini 3 Flash and GPT-5 mini. The best open-source baseline, Qwen3-VL-32B-Instruct, reaches 39.0. Config tasks are the hardest scenario.
- On TVWorld-G (187 samples, Acc@0.5), TVTheseus scores 81.8 versus 78.1 for its base model, even though it received no grounding supervision.
- Training traces target three behaviours: goal-directed focus moves, recovery from detours, and escaping stalled states. In the ablation, SFT alone gives 48.0 on TVWorld-N and 83.4 on TVWorld-G. Adding RL raises TVWorld-N to 68.3, with a slight drop in grounding.
- Point-and-click agents such as GUI-Owl and OpenCUA degrade sharply in the remote-control setting. Code is released at github.com/Lqf-HFNJU/TVTheseus.

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

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 626 works

## Cite

Cite as: Zhantao Ma, Quanfeng Lu, Shuai Zhong, Dahai Yu, Ping Luo and Michael Ng. 2026. TVWorld: Foundations for Remote-Control TV Agents. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ma2026tvworld,
  title = {{TVWorld: Foundations for Remote-Control TV Agents}},
  author = {Zhantao Ma, Quanfeng Lu, Shuai Zhong, Dahai Yu, Ping Luo and Michael Ng},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1792},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1792}
}
```

- [← previous TutlAit v1: a crowdsourced Moroccan Tamazight speech dataset with Arabic transcriptions and regional accent labels](https://md.research.elamur.ai/free/en/papers/chadi-2026-tutlait-v1-crowdsourced-moroccan-tamazight/)
- [next → Twenty Years of HAREM: A Reproducible Audit and Reassessment of Portuguese Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/nunes-2026-twenty-years-harem-reproducible-audit/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/54/)

## References

72 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tamer Abuelsaad, Deepak Akkil, Prasenjit Dey, Ashish Jagmohan, Aditya Vempaty, and Ravi Kokku. 2024. Agent-e: From autonomous web navigation to foundational design principles in agentic systems. arXiv preprint arXiv:2407.13032. — [arXiv:2407.13032](https://arxiv.org/abs/2407.13032) [find](https://scholar.google.com/scholar?q=Tamer+Abuelsaad%2C+Deepak+Akkil%2C+Prasenjit+Dey%2C+Ashish+Jagmohan%2C+Aditya+Vempaty%2C+and+Ravi+Kokku%2E+2024%2E+Agent%2De%3A+From+autonomous+web+navigation+to+foundational+design+principles+in+agentic+systems%2E+arXiv)
2. David Adamo, Md Khorrom Khan, Sreedevi Koppula, and Renée Bryce. 2018. Reinforcement learning for android gui testing. In Proceedings of the 9th ACM SIGSOFT international workshop on automating TEST case design, selection, and evaluation, pages 2–8. [find](https://scholar.google.com/scholar?q=David+Adamo%2C+Md+Khorrom+Khan%2C+Sreedevi+Koppula%2C+and+Ren%C3%A9e+Bryce%2E+2018%2E+Reinforcement+learning+for+android+gui+testing%2E+In+Proceedings+of+the+9th+ACM+SIGSOFT+international+workshop+on+automating+TEST+c)
3. Saaket Agashe, Jiuzhou Han, Shuyu Gan, Jiachen Yang, Ang Li, and Xin Eric Wang. 2024. Agent s: An open agentic framework that uses computers like a human. arXiv preprint arXiv:2410.08164. — [arXiv:2410.08164](https://arxiv.org/abs/2410.08164) [find](https://scholar.google.com/scholar?q=Saaket+Agashe%2C+Jiuzhou+Han%2C+Shuyu+Gan%2C+Jiachen+Yang%2C+Ang+Li%2C+and+Xin+Eric+Wang%2E+2024%2E+Agent+s%3A+An+open+agentic+framework+that+uses+computers+like+a+human%2E+arXiv+preprint+arXiv%3A2410%2E08164%2E+%E2%80%94+%5BarXiv%3A241)
4. Bestoun S Ahmed, Angelo Gargantini, and Miroslav Bures. 2020. An automated testing framework for smart tv apps based on model separation. In 2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), pages 62–73. IEEE. [find](https://scholar.google.com/scholar?q=Bestoun+S+Ahmed%2C+Angelo+Gargantini%2C+and+Miroslav+Bures%2E+2020%2E+An+automated+testing+framework+for+smart+tv+apps+based+on+model+separation%2E+In+2020+IEEE+International+Conference+on+Software+Testing%2C+Ver)
5. Keith T Butler, Daniel W Davies, Hugh Cartwright, Olexandr Isayev, and Aron Walsh. 2018. Machine learning for molecular and materials science. Nature, 559(7715):547–555. [find](https://scholar.google.com/scholar?q=Keith+T+Butler%2C+Daniel+W+Davies%2C+Hugh+Cartwright%2C+Olexandr+Isayev%2C+and+Aron+Walsh%2E+2018%2E+Machine+learning+for+molecular+and+materials+science%2E+Nature%2C+559%287715%29%3A547%E2%80%93555%2E)
6. Cong Chen, Kaixiang Ji, Hao Zhong, Muzhi Zhu, Anzhou Li, Guo Gan, Ziyuan Huang, Cheng Zou, Jiajia Liu, Jingdong Chen, and 1 others. 2025. Gui-shepherd: Reliable process reward and verification for long-sequence gui tasks. arXiv preprint arXiv:2509.23738. — [arXiv:2509.23738](https://arxiv.org/abs/2509.23738) [find](https://scholar.google.com/scholar?q=Cong+Chen%2C+Kaixiang+Ji%2C+Hao+Zhong%2C+Muzhi+Zhu%2C+Anzhou+Li%2C+Guo+Gan%2C+Ziyuan+Huang%2C+Cheng+Zou%2C+Jiajia+Liu%2C+Jingdong+Chen%2C+and+1+others%2E+2025%2E+Gui%2Dshepherd%3A+Reliable+process+reward+and+verification+for+lon)
7. Dongping Chen, Yue Huang, Siyuan Wu, Jingyu Tang, Liuyi Chen, Yilin Bai, Zhigang He, Chenlong Wang, Huichi Zhou, Yiqiang Li, and 1 others. 2024. Gui-world: A video benchmark and dataset for multimodal gui-oriented understanding. arXiv preprint arXiv:2406.10819. — [arXiv:2406.10819](https://arxiv.org/abs/2406.10819) [find](https://scholar.google.com/scholar?q=Dongping+Chen%2C+Yue+Huang%2C+Siyuan+Wu%2C+Jingyu+Tang%2C+Liuyi+Chen%2C+Yilin+Bai%2C+Zhigang+He%2C+Chenlong+Wang%2C+Huichi+Zhou%2C+Yiqiang+Li%2C+and+1+others%2E+2024%2E+Gui%2Dworld%3A+A+video+benchmark+and+dataset+for+multimodal)
8. Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Li YanTao, Jianbing Zhang, and Zhiyong Wu. 2024. [Seeclick: Harnessing gui grounding for advanced visual gui agents](https://md.research.elamur.ai/free/en/papers/cheng-2024-seeclick-harnessing-gui-grounding-advanced/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9313–9332.
9. Reid Andersen, Fan Chung, and Kevin Lang. 2006. Local graph partitioning using pagerank vectors. In 2006 47th annual IEEE symposium on foundations of computer science (FOCS’06), pages 475–486. IEEE. [find](https://scholar.google.com/scholar?q=Reid+Andersen%2C+Fan+Chung%2C+and+Kevin+Lang%2E+2006%2E+Local+graph+partitioning+using+pagerank+vectors%2E+In+2006+47th+annual+IEEE+symposium+on+foundations+of+computer+science+%28FOCS%E2%80%9906%29%2C+pages+475%E2%80%93486%2E+IEEE%2E)
10. Victor-Alexandru Darvariu, Stephen Hailes, and Mirco Musolesi. 2021. Goal-directed graph construction using reinforcement learning. Proceedings of the Royal Society A, 477(2254):20210168. [find](https://scholar.google.com/scholar?q=Victor%2DAlexandru+Darvariu%2C+Stephen+Hailes%2C+and+Mirco+Musolesi%2E+2021%2E+Goal%2Ddirected+graph+construction+using+reinforcement+learning%2E+Proceedings+of+the+Royal+Society+A%2C+477%282254%29%3A20210168%2E)
11. Anthropic. 2025. Claude. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Claude%2E)
12. Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, and Andrew McCallum. 2017. Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. arXiv preprint arXiv:1711.05851. [find](https://scholar.google.com/scholar?q=Rajarshi+Das%2C+Shehzaad+Dhuliawala%2C+Manzil+Zaheer%2C+Luke+Vilnis%2C+Ishan+Durugkar%2C+Akshay+Krishnamurthy%2C+Alex+Smola%2C+and+Andrew+McCallum%2E+2017%2E+Go+for+a+walk+and+arrive+at+the+answer%3A+Reasoning+over+paths)
13. Gilles Baechler, Srinivas Sunkara, Maria Wang, Fedir Zubach, Hassan Mansoor, Vincent Etter, Victor Cărbune, Jason Lin, Jindong Chen, and Abhanshu Sharma. 2024. Screenai: A vision-language model for ui and infographics understanding. arXiv preprint arXiv:2402.04615. — [arXiv:2402.04615](https://arxiv.org/abs/2402.04615) [find](https://scholar.google.com/scholar?q=Gilles+Baechler%2C+Srinivas+Sunkara%2C+Maria+Wang%2C+Fedir+Zubach%2C+Hassan+Mansoor%2C+Vincent+Etter%2C+Victor+Ca%CC%86rbune%2C+Jason+Lin%2C+Jindong+Chen%2C+and+Abhanshu+Sharma%2E+2024%2E+Screenai%3A+A+vision%2Dlanguage+model+for+u)
14. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, and 45 others. 2025. [Qwen3-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen3-vl-technical-report/). arXiv prepri…
15. Avrim Blum, John Hopcroft, and Ravindran Kannan. 2020. Foundations of data science. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Avrim+Blum%2C+John+Hopcroft%2C+and+Ravindran+Kannan%2E+2020%2E+Foundations+of+data+science%2E+Cambridge+University+Press%2E)
16. Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, Arthur Bucker, and 1 others. 2024. Windows agent arena: Evaluating multi-modal os agents at scale. arXiv preprint arXiv:2409.08264. — [arXiv:2409.08264](https://arxiv.org/abs/2409.08264) [find](https://scholar.google.com/scholar?q=Rogerio+Bonatti%2C+Dan+Zhao%2C+Francesco+Bonacci%2C+Dillon+Dupont%2C+Sara+Abdali%2C+Yinheng+Li%2C+Yadong+Lu%2C+Justin+Wagle%2C+Kazuhito+Koishida%2C+Arthur+Bucker%2C+and+1+others%2E+2024%2E+Windows+agent+arena%3A+Evaluating+mul)
17. Miroslav Bures, Miroslav Macik, Bestoun S Ahmed, Vaclav Rechtberger, and Pavel Slavik. 2020. Testing the usability and accessibility of smart tv applications using an automated model-based approach. IEEE transactions on consumer electronics, 66(2):134–143. [find](https://scholar.google.com/scholar?q=Miroslav+Bures%2C+Miroslav+Macik%2C+Bestoun+S+Ahmed%2C+Vaclav+Rechtberger%2C+and+Pavel+Slavik%2E+2020%2E+Testing+the+usability+and+accessibility+of+smart+tv+applications+using+an+automated+model%2Dbased+approach%2E+I)
18. Rati Devidze, Goran Radanovic, Parameswaran Kamalaruban, and Adish Singla. 2021. Explicable reward design for reinforcement learning agents. Advances in neural information processing systems, 34:20118–20131. [find](https://scholar.google.com/scholar?q=Rati+Devidze%2C+Goran+Radanovic%2C+Parameswaran+Kamalaruban%2C+and+Adish+Singla%2E+2021%2E+Explicable+reward+design+for+reinforcement+learning+agents%2E+Advances+in+neural+information+processing+systems%2C+34%3A20118)
19. Atıl Fırat, Mohammad Yusaf Azimi, Celal Çağın Elgün, Ferhat Erata, and Cemal Yılmaz. 2022. Model-based test adaptation for smart tvs. In Proceedings of the 3rd ACM/IEEE International Conference on Automation of Software Test, pages 52–53. [find](https://scholar.google.com/scholar?q=At%C4%B1l+F%C4%B1rat%2C+Mohammad+Yusaf+Azimi%2C+Celal+%C3%87ag%CC%86%C4%B1n+Elg%C3%BCn%2C+Ferhat+Erata%2C+and+Cemal+Y%C4%B1lmaz%2E+2022%2E+Model%2Dbased+test+adaptation+for+smart+tvs%2E+In+Proceedings+of+the+3rd+ACM%2FIEEE+International+Conference+on+Au)
20. Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, and Yu Su. 2024. [Navigating the digital world as humans do: Universal visual grounding for gui agents](https://md.research.elamur.ai/free/en/papers/gou-2024-navigating-digital-world-humans-universal/). arXiv preprint arXiv:2410.05243.
21. Izzeddin Gur, Ulrich Rueckert, Aleksandra Faust, and Dilek Hakkani-Tur. 2018. Learning to navigate the web. arXiv preprint arXiv:1812.09195. — [arXiv:1812.09195](https://arxiv.org/abs/1812.09195) [find](https://scholar.google.com/scholar?q=Izzeddin+Gur%2C+Ulrich+Rueckert%2C+Aleksandra+Faust%2C+and+Dilek+Hakkani%2DTur%2E+2018%2E+Learning+to+navigate+the+web%2E+arXiv+preprint+arXiv%3A1812%2E09195%2E+%E2%80%94+%5BarXiv%3A1812%2E09195%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1812%2E09195%29)
22. Jihye Hong and Florian Rivoal. 2019. CSS spatial navigation level 1. W3C Working Draft. [find](https://scholar.google.com/scholar?q=Jihye+Hong+and+Florian+Rivoal%2E+2019%2E+CSS+spatial+navigation+level+1%2E+W3C+Working+Draft%2E)
23. Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxiao Dong, Ming Ding, and 1 others. 2024. [Cogagent: A visual language model for gui agents](https://md.research.elamur.ai/free/en/papers/hong-2023-cogagent-visual-language-model/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14281–14290.
24. Jumman Hossain, Abu-Zaher Faridee, Nirmalya Roy, Jade Freeman, Timothy Gregory, and Theron Trout. 2024. Toponav: Topological navigation for efficient exploration in sparse reward environments. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 693–700. IEEE. [find](https://scholar.google.com/scholar?q=Jumman+Hossain%2C+Abu%2DZaher+Faridee%2C+Nirmalya+Roy%2C+Jade+Freeman%2C+Timothy+Gregory%2C+and+Theron+Trout%2E+2024%2E+Toponav%3A+Topological+navigation+for+efficient+exploration+in+sparse+reward+environments%2E+In+2024)
25. Sheng Jia, Jamie Kiros, and Jimmy Ba. 2019. Dom-q-net: Grounded rl on structured language. arXiv preprint arXiv:1902.07257. [find](https://scholar.google.com/scholar?q=Sheng+Jia%2C+Jamie+Kiros%2C+and+Jimmy+Ba%2E+2019%2E+Dom%2Dq%2Dnet%3A+Grounded+rl+on+structured+language%2E+arXiv+preprint+arXiv%3A1902%2E07257%2E)
26. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
27. Hyunseok Lee, Jeonghoon Kim, Beomjun Kim, Jihoon Tack, Chansong Jo, Jaehong Lee, Cheonbok Park, Sookyo In, Jinwoo Shin, and Kang Min Yoo. 2025. Reguide: Data efficient gui grounding via spatial reasoning and search. arXiv preprint arXiv:2505.15259. — [arXiv:2505.15259](https://arxiv.org/abs/2505.15259) [find](https://scholar.google.com/scholar?q=Hyunseok+Lee%2C+Jeonghoon+Kim%2C+Beomjun+Kim%2C+Jihoon+Tack%2C+Chansong+Jo%2C+Jaehong+Lee%2C+Cheonbok+Park%2C+Sookyo+In%2C+Jinwoo+Shin%2C+and+Kang+Min+Yoo%2E+2025%2E+Reguide%3A+Data+efficient+gui+grounding+via+spatial+reason)
28. Wei Li, William E Bishop, Alice Li, Christopher Rawles, Folawiyo Campbell-Ajala, Divya Tyamagundlu, and Oriana Riva. 2024a. [On the effects of data scale on ui control agents](https://md.research.elamur.ai/free/en/papers/li-2024-effects-data-scale-ui-control/). Advances in Neural Information Processing Systems, 37:92130–92154.
29. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yutao Zhu, Yongkang Wu, Ji-Rong Wen, and Zhicheng Dou. 2025. [Webthinker: Empowering large reasoning models with deep research capability](https://md.research.elamur.ai/free/en/papers/li-2025-webthinker-empowering-large-reasoning-models/). arXiv preprint arXiv:2504.21776.
30. Zhangheng Li, Keen You, Haotian Zhang, Di Feng, Harsh Agrawal, Xiujun Li, Mohana Prasad Sathya Moorthy, Jeff Nichols, Yinfei Yang, and Zhe Gan. 2024b. Ferret-ui 2: Mastering universal user interface understanding across platforms. arXiv preprint arXiv:2410.18967. — [arXiv:2410.18967](https://arxiv.org/abs/2410.18967) [find](https://scholar.google.com/scholar?q=Zhangheng+Li%2C+Keen+You%2C+Haotian+Zhang%2C+Di+Feng%2C+Harsh+Agrawal%2C+Xiujun+Li%2C+Mohana+Prasad+Sathya+Moorthy%2C+Jeff+Nichols%2C+Yinfei+Yang%2C+and+Zhe+Gan%2E+2024b%2E+Ferret%2Dui+2%3A+Mastering+universal+user+interface+u)
31. Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, and Percy Liang. 2018. [Reinforcement learning on web interfaces using workflow-guided exploration](https://md.research.elamur.ai/free/en/papers/liu-2018-reinforcement-learning-web-interfaces-using/). In International Conference on Learning Representations (ICLR).
32. Yuhang Liu, Pengxiang Li, Congkai Xie, Xavier Hu, Xiaotian Han, Shengyu Zhang, Hongxia Yang, and Fei Wu. 2025. Infigui-r1: Advancing multimodal gui agents from reactive actors to deliberative reasoners. arXiv preprint arXiv:2504.14239. — [arXiv:2504.14239](https://arxiv.org/abs/2504.14239) [find](https://scholar.google.com/scholar?q=Yuhang+Liu%2C+Pengxiang+Li%2C+Congkai+Xie%2C+Xavier+Hu%2C+Xiaotian+Han%2C+Shengyu+Zhang%2C+Hongxia+Yang%2C+and+Fei+Wu%2E+2025%2E+Infigui%2Dr1%3A+Advancing+multimodal+gui+agents+from+reactive+actors+to+deliberative+reasoner)
33. 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. arXiv preprint arXiv:2505.16282. — [arXiv:2505.16282](https://arxiv.org/abs/2505.16282) [find](https://scholar.google.com/scholar?q=Fanbin+Lu%2C+Zhisheng+Zhong%2C+Shu+Liu%2C+Chi%2DWing+Fu%2C+and+Jiaya+Jia%2E+2025a%2E+Arpo%3A+End%2Dto%2Dend+policy+optimization+for+gui+agents+with+experience+replay%2E+arXiv+preprint+arXiv%3A2505%2E16282%2E+%E2%80%94+%5BarXiv%3A2505%2E16282%5D)
34. Fanbin Lu, Zhisheng Zhong, Ziqin Wei, Shu Liu, Chi-Wing Fu, and Jiaya Jia. 2025b. Steve: A step verification pipeline for computer-use agent training. arXiv preprint arXiv:2503.12532. — [arXiv:2503.12532](https://arxiv.org/abs/2503.12532) [find](https://scholar.google.com/scholar?q=Fanbin+Lu%2C+Zhisheng+Zhong%2C+Ziqin+Wei%2C+Shu+Liu%2C+Chi%2DWing+Fu%2C+and+Jiaya+Jia%2E+2025b%2E+Steve%3A+A+step+verification+pipeline+for+computer%2Duse+agent+training%2E+arXiv+preprint+arXiv%3A2503%2E12532%2E+%E2%80%94+%5BarXiv%3A2503%2E12)
35. Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K Ng, and Ping Luo. 2025c. Swirl: A staged workflow for interleaved reinforcement learning in mobile gui control. arXiv preprint arXiv:2508.20018. — [arXiv:2508.20018](https://arxiv.org/abs/2508.20018) [find](https://scholar.google.com/scholar?q=Quanfeng+Lu%2C+Zhantao+Ma%2C+Shuai+Zhong%2C+Jin+Wang%2C+Dahai+Yu%2C+Michael+K+Ng%2C+and+Ping+Luo%2E+2025c%2E+Swirl%3A+A+staged+workflow+for+interleaved+reinforcement+learning+in+mobile+gui+control%2E+arXiv+preprint+arXiv)
36. Quanfeng Lu, Wenqi Shao, Zitao Liu, Lingxiao Du, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, and Ping Luo. 2025d. 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](https://scholar.google.com/scholar?q=Quanfeng+Lu%2C+Wenqi+Shao%2C+Zitao+Liu%2C+Lingxiao+Du%2C+Fanqing+Meng%2C+Boxuan+Li%2C+Botong+Chen%2C+Siyuan+Huang%2C+Kaipeng+Zhang%2C+and+Ping+Luo%2E+2025d%2E+Guiodyssey%3A+A+comprehensive+dataset+for+cross%2Dapp+gui+navigatio)
37. Zhengxi Lu, Yuxiang Chai, Yaxuan Guo, Xi Yin, Liang Liu, Hao Wang, Han Xiao, Shuai Ren, Pengxiang Zhao, Guangyi Liu, and 1 others. 2026. Ui-r1: Enhancing efficient action prediction of gui agents by reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40,… [find](https://scholar.google.com/scholar?q=Zhengxi+Lu%2C+Yuxiang+Chai%2C+Yaxuan+Guo%2C+Xi+Yin%2C+Liang+Liu%2C+Hao+Wang%2C+Han+Xiao%2C+Shuai+Ren%2C+Pengxiang+Zhao%2C+Guangyi+Liu%2C+and+1+others%2E+2026%2E+Ui%2Dr1%3A+Enhancing+efficient+action+prediction+of+gui+agents+by+r)
38. Run Luo, Lu Wang, Wanwei He, and Xiaobo Xia. 2025. Gui-r1: A generalist r1-style vision-language action model for gui agents. arXiv preprint arXiv:2504.10458. — [arXiv:2504.10458](https://arxiv.org/abs/2504.10458) [find](https://scholar.google.com/scholar?q=Run+Luo%2C+Lu+Wang%2C+Wanwei+He%2C+and+Xiaobo+Xia%2E+2025%2E+Gui%2Dr1%3A+A+generalist+r1%2Dstyle+vision%2Dlanguage+action+model+for+gui+agents%2E+arXiv+preprint+arXiv%3A2504%2E10458%2E+%E2%80%94+%5BarXiv%3A2504%2E10458%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
39. Jakob Nyberg and Pontus Johnson. 2023. Training automated defense strategies using graph-based cyber attack simulations. arXiv preprint arXiv:2304.11084. — [arXiv:2304.11084](https://arxiv.org/abs/2304.11084) [find](https://scholar.google.com/scholar?q=Jakob+Nyberg+and+Pontus+Johnson%2E+2023%2E+Training+automated+defense+strategies+using+graph%2Dbased+cyber+attack+simulations%2E+arXiv+preprint+arXiv%3A2304%2E11084%2E+%E2%80%94+%5BarXiv%3A2304%2E11084%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F230)
40. Minxue Pan, An Huang, Guoxin Wang, Tian Zhang, and Xuandong Li. 2020. Reinforcement learning based curiosity-driven testing of android applications. In Proceedings of the 29th ACM SIGSOFT international symposium on software testing and analysis, pages 153–164. [find](https://scholar.google.com/scholar?q=Minxue+Pan%2C+An+Huang%2C+Guoxin+Wang%2C+Tian+Zhang%2C+and+Xuandong+Li%2E+2020%2E+Reinforcement+learning+based+curiosity%2Ddriven+testing+of+android+applications%2E+In+Proceedings+of+the+29th+ACM+SIGSOFT+internationa)
41. Georgios Papoudakis, Thomas Coste, Zhihao Wu, Jianye Hao, Jun Wang, and Kun Shao. 2025. Appvlm: A lightweight vision language model for online app control. arXiv preprint arXiv:2502.06395. — [arXiv:2502.06395](https://arxiv.org/abs/2502.06395) [find](https://scholar.google.com/scholar?q=Georgios+Papoudakis%2C+Thomas+Coste%2C+Zhihao+Wu%2C+Jianye+Hao%2C+Jun+Wang%2C+and+Kun+Shao%2E+2025%2E+Appvlm%3A+A+lightweight+vision+language+model+for+online+app+control%2E+arXiv+preprint+arXiv%3A2502%2E06395%2E+%E2%80%94+%5BarXiv%3A25)
42. Christopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair, Alice Li, William Bishop, Wei Li, Folawiyo Campbell-Ajala, and 1 others. 2024. [Androidworld: A dynamic benchmarking environment for autonomous agents](https://md.research.elamur.ai/free/en/papers/rawles-2024-androidworld-dynamic-benchmarking-environment-autonomous/). arXiv preprint arXiv:2405.14573.
43. Thassilo M Schiepanski and Nicholas Piël. 2025. Beyond pixels: Exploring dom downsampling for llm-based web agents. arXiv preprint arXiv:2508.04412. — [arXiv:2508.04412](https://arxiv.org/abs/2508.04412) [find](https://scholar.google.com/scholar?q=Thassilo+M+Schiepanski+and+Nicholas+Pi%C3%ABl%2E+2025%2E+Beyond+pixels%3A+Exploring+dom+downsampling+for+llm%2Dbased+web+agents%2E+arXiv+preprint+arXiv%3A2508%2E04412%2E+%E2%80%94+%5BarXiv%3A2508%2E04412%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2508%2E044)
44. ByteDance Seed. 2025. seed-tars.com/1.5. [find](https://scholar.google.com/scholar?q=ByteDance+Seed%2E+2025%2E+seed%2Dtars%2Ecom%2F1%2E5%2E)
45. Dhruv Shah, Benjamin Eysenbach, Gregory Kahn, Nicholas Rhinehart, and Sergey Levine. 2021. Ving: Learning open-world navigation with visual goals. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 13215–13222. IEEE. [find](https://scholar.google.com/scholar?q=Dhruv+Shah%2C+Benjamin+Eysenbach%2C+Gregory+Kahn%2C+Nicholas+Rhinehart%2C+and+Sergey+Levine%2E+2021%2E+Ving%3A+Learning+open%2Dworld+navigation+with+visual+goals%2E+In+2021+IEEE+International+Conference+on+Robotics+and)
46. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
47. Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh J Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, and 1 others. 2024. [Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments](https://md.research.elamur.ai/free/en/papers/xie-2024-osworld-benchmarking-multimodal-agents-open/). Advances in Neural Information Processing Systems, 37…
48. Wenhan Xiong, Thien Hoang, and William Yang Wang. 2017. Deeppath: A reinforcement learning method for knowledge graph reasoning. arXiv preprint arXiv:1707.06690. [find](https://scholar.google.com/scholar?q=Wenhan+Xiong%2C+Thien+Hoang%2C+and+William+Yang+Wang%2E+2017%2E+Deeppath%3A+A+reinforcement+learning+method+for+knowledge+graph+reasoning%2E+arXiv+preprint+arXiv%3A1707%2E06690%2E)
49. Peter Shaw, Mandar Joshi, James Cohan, Jonathan Berant, Panupong Pasupat, Hexiang Hu, Urvashi Khandelwal, Kenton Lee, and Kristina N Toutanova. 2023. From pixels to ui actions: Learning to follow instructions via graphical user interfaces. Advances in Neural Information Processing Systems, 36:34354–… [find](https://scholar.google.com/scholar?q=Peter+Shaw%2C+Mandar+Joshi%2C+James+Cohan%2C+Jonathan+Berant%2C+Panupong+Pasupat%2C+Hexiang+Hu%2C+Urvashi+Khandelwal%2C+Kenton+Lee%2C+and+Kristina+N+Toutanova%2E+2023%2E+From+pixels+to+ui+actions%3A+Learning+to+follow+inst)
50. Tianqi Xu, Linyao Chen, Dai-Jie Wu, Yanjun Chen, Zecheng Zhang, Xiang Yao, Zhiqiang Xie, Yongchao Chen, Shilong Liu, Bochen Qian, and 1 others. 2025. Crab: Cross-environment agent benchmark for multimodal language model agents. In Findings of the Association for Computational Linguistics: ACL 2025,… [find](https://scholar.google.com/scholar?q=Tianqi+Xu%2C+Linyao+Chen%2C+Dai%2DJie+Wu%2C+Yanjun+Chen%2C+Zecheng+Zhang%2C+Xiang+Yao%2C+Zhiqiang+Xie%2C+Yongchao+Chen%2C+Shilong+Liu%2C+Bochen+Qian%2C+and+1+others%2E+2025%2E+Crab%3A+Cross%2Denvironment+agent+benchmark+for+multim)
51. 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](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). In Proceedings of the Twentieth European Conference on Computer Systems, pages 1279–1297.
52. Xiaoyu Xu, Hao Hu, Yuling Liu, Jinglei Tan, Hongqi Zhang, and Haotian Song. 2022. Moving target defense of routing randomization with deep reinforcement learning against eavesdropping attack. Digital Communications and Networks, 8(3):373–387. [find](https://scholar.google.com/scholar?q=Xiaoyu+Xu%2C+Hao+Hu%2C+Yuling+Liu%2C+Jinglei+Tan%2C+Hongqi+Zhang%2C+and+Haotian+Song%2E+2022%2E+Moving+target+defense+of+routing+randomization+with+deep+reinforcement+learning+against+eavesdropping+attack%2E+Digital+)
53. Joykirat Singh, Raghav Magazine, Yash Pandya, and Akshay Nambi. 2025. Agentic reasoning and tool integration for llms via reinforcement learning. arXiv preprint arXiv:2505.01441. — [arXiv:2505.01441](https://arxiv.org/abs/2505.01441) [find](https://scholar.google.com/scholar?q=Joykirat+Singh%2C+Raghav+Magazine%2C+Yash+Pandya%2C+and+Akshay+Nambi%2E+2025%2E+Agentic+reasoning+and+tool+integration+for+llms+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2505%2E01441%2E+%E2%80%94+%5BarXiv%3A2505%2E01441%5D%28)
54. Strategy Analytics, Inc. 2021. Strategy analytics: Global smart TV household ownership to exceed 50% by 2026. Business Wire press release. [find](https://scholar.google.com/scholar?q=Strategy+Analytics%2C+Inc%2E+2021%2E+Strategy+analytics%3A+Global+smart+TV+household+ownership+to+exceed+50%25+by+2026%2E+Business+Wire+press+release%2E)
55. Hanghang Tong, Christos Faloutsos, and Jia-Yu Pan. 2006. Fast random walk with restart and its applications. In Sixth international conference on data mining (ICDM’06), pages 613–622. IEEE. [find](https://scholar.google.com/scholar?q=Hanghang+Tong%2C+Christos+Faloutsos%2C+and+Jia%2DYu+Pan%2E+2006%2E+Fast+random+walk+with+restart+and+its+applications%2E+In+Sixth+international+conference+on+data+mining+%28ICDM%E2%80%9906%29%2C+pages+613%E2%80%93622%2E+IEEE%2E)
56. Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, and 1 others. 2025a. [Ui-tars-2 technical report: Advancing gui agent with multi-turn reinforcement learning](https://md.research.elamur.ai/free/en/papers/wang-2025-ui-tars-2-technical/). arXiv preprint arXiv:2509.02544.
57. Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang, Tianbao Xie, Junli Wang, Jiaqi Deng, Xiaole Guo, Yiheng Xu, Chen Henry Wu, and 1 others. 2025b. Opencua: Open foundations for computer-use agents. arXiv preprint arXiv:2508.09123. [find](https://scholar.google.com/scholar?q=Xinyuan+Wang%2C+Bowen+Wang%2C+Dunjie+Lu%2C+Junlin+Yang%2C+Tianbao+Xie%2C+Junli+Wang%2C+Jiaqi+Deng%2C+Xiaole+Guo%2C+Yiheng+Xu%2C+Chen+Henry+Wu%2C+and+1+others%2E+2025b%2E+Opencua%3A+Open+foundations+for+computer%2Duse+agents%2E+arX)
58. Yiqin Wang, Haoji Zhang, Jingqi Tian, and Yansong Tang. 2025c. Ponder & press: Advancing visual gui agent towards general computer control. In Findings of the Association for Computational Linguistics: ACL 2025, pages 1461–1473. [find](https://scholar.google.com/scholar?q=Yiqin+Wang%2C+Haoji+Zhang%2C+Jingqi+Tian%2C+and+Yansong+Tang%2E+2025c%2E+Ponder+%26+press%3A+Advancing+visual+gui+agent+towards+general+computer+control%2E+In+Findings+of+the+Association+for+Computational+Linguistics)
59. Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, and 1 others. 2024. [Os-atlas: A foundation action model for generalist gui agents](https://md.research.elamur.ai/free/en/papers/wu-2024-os-atlas-foundation-action-model/). arXiv preprint arXiv:2410.23218.
60. Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, Dawn Song, Huan Sun, and Yu Su. 2025. An illusion of progress? assessing the current state of web agents. arXiv preprint arXiv:2504.01382. [find](https://scholar.google.com/scholar?q=Tianci+Xue%2C+Weijian+Qi%2C+Tianneng+Shi%2C+Chan+Hee+Song%2C+Boyu+Gou%2C+Dawn+Song%2C+Huan+Sun%2C+and+Yu+Su%2E+2025%2E+An+illusion+of+progress%3F+assessing+the+current+state+of+web+agents%2E+arXiv+preprint+arXiv%3A2504%2E01382)
61. Shanchao Yang, MA Kaili, Baoxiang Wang, Tianshu Yu, and Hongyuan Zha. 2023. Learning to boost resilience of complex networks via neural edge rewiring. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Shanchao+Yang%2C+MA+Kaili%2C+Baoxiang+Wang%2C+Tianshu+Yu%2C+and+Hongyuan+Zha%2E+2023%2E+Learning+to+boost+resilience+of+complex+networks+via+neural+edge+rewiring%2E+Transactions+on+Machine+Learning+Research%2E)
62. Jiabo Ye, Xi Zhang, Haiyang Xu, Haowei Liu, Junyang Wang, Zhaoqing Zhu, Ziwei Zheng, Feiyu Gao, Junjie Cao, Zhengxi Lu, and 1 others. 2025. Mobile-agent-v3: Foundamental agents for gui automation. arXiv preprint arXiv:2508.15144. — [arXiv:2508.15144](https://arxiv.org/abs/2508.15144) [find](https://scholar.google.com/scholar?q=Jiabo+Ye%2C+Xi+Zhang%2C+Haiyang+Xu%2C+Haowei+Liu%2C+Junyang+Wang%2C+Zhaoqing+Zhu%2C+Ziwei+Zheng%2C+Feiyu+Gao%2C+Junjie+Cao%2C+Zhengxi+Lu%2C+and+1+others%2E+2025%2E+Mobile%2Dagent%2Dv3%3A+Foundamental+agents+for+gui+automation%2E+arX)
63. Jiaxuan You, Bowen Liu, Zhitao Ying, Vijay Pande, and Jure Leskovec. 2018. Graph convolutional policy network for goal-directed molecular graph generation. Advances in neural information processing systems, 31. [find](https://scholar.google.com/scholar?q=Jiaxuan+You%2C+Bowen+Liu%2C+Zhitao+Ying%2C+Vijay+Pande%2C+and+Jure+Leskovec%2E+2018%2E+Graph+convolutional+policy+network+for+goal%2Ddirected+molecular+graph+generation%2E+Advances+in+neural+information+processing+sy)
64. Siliang Zeng, Quan Wei, William Brown, Oana Frunza, Yuriy Nevmyvaka, and Mingyi Hong. 2025. Reinforcing multi-turn reasoning in llm agents via turn-level credit assignment. arXiv preprint arXiv:2505.11821. — [arXiv:2505.11821](https://arxiv.org/abs/2505.11821) [find](https://scholar.google.com/scholar?q=Siliang+Zeng%2C+Quan+Wei%2C+William+Brown%2C+Oana+Frunza%2C+Yuriy+Nevmyvaka%2C+and+Mingyi+Hong%2E+2025%2E+Reinforcing+multi%2Dturn+reasoning+in+llm+agents+via+turn%2Dlevel+credit+assignment%2E+arXiv+preprint+arXiv%3A2505%2E1)
65. Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, and 1 others. 2025a. Ufo2: The desktop agentos. arXiv preprint arXiv:2504.14603. — [arXiv:2504.14603](https://arxiv.org/abs/2504.14603) [find](https://scholar.google.com/scholar?q=Chaoyun+Zhang%2C+He+Huang%2C+Chiming+Ni%2C+Jian+Mu%2C+Si+Qin%2C+Shilin+He%2C+Lu+Wang%2C+Fangkai+Yang%2C+Pu+Zhao%2C+Chao+Du%2C+and+1+others%2E+2025a%2E+Ufo2%3A+The+desktop+agentos%2E+arXiv+preprint+arXiv%3A2504%2E14603%2E+%E2%80%94+%5BarXiv%3A2504)
66. Danqing Zhang, Balaji Rama, Jingyi Ni, Shiying He, Fu Zhao, Kunyu Chen, Arnold Chen, and Junyu Cao. 2025b. Litewebagent: The open-source suite for vlm-based web-agent applications. arXiv preprint arXiv:2503.02950. [find](https://scholar.google.com/scholar?q=Danqing+Zhang%2C+Balaji+Rama%2C+Jingyi+Ni%2C+Shiying+He%2C+Fu+Zhao%2C+Kunyu+Chen%2C+Arnold+Chen%2C+and+Junyu+Cao%2E+2025b%2E+Litewebagent%3A+The+open%2Dsource+suite+for+vlm%2Dbased+web%2Dagent+applications%2E+arXiv+preprint+arXi)
67. Danyang Zhang, Situo Zhang, Ziyue Yang, Zichen Zhu, Zihan Zhao, Ruisheng Cao, Lu Chen, and Kai Yu. 2025c. Progrm: Build better gui agents with progress rewards. arXiv preprint arXiv:2505.18121. — [arXiv:2505.18121](https://arxiv.org/abs/2505.18121) [find](https://scholar.google.com/scholar?q=Danyang+Zhang%2C+Situo+Zhang%2C+Ziyue+Yang%2C+Zichen+Zhu%2C+Zihan+Zhao%2C+Ruisheng+Cao%2C+Lu+Chen%2C+and+Kai+Yu%2E+2025c%2E+Progrm%3A+Build+better+gui+agents+with+progress+rewards%2E+arXiv+preprint+arXiv%3A2505%2E18121%2E+%E2%80%94+%5BarX)
68. Jiwen Zhang, Jihao Wu, Yihua Teng, Minghui Liao, Nuo Xu, Xiao Xiao, Zhongyu Wei, and Duyu Tang. 2024. Android in the zoo: Chain-of-action-thought for gui agents. arXiv preprint arXiv:2403.02713. [find](https://scholar.google.com/scholar?q=Jiwen+Zhang%2C+Jihao+Wu%2C+Yihua+Teng%2C+Minghui+Liao%2C+Nuo+Xu%2C+Xiao+Xiao%2C+Zhongyu+Wei%2C+and+Duyu+Tang%2E+2024%2E+Android+in+the+zoo%3A+Chain%2Dof%2Daction%2Dthought+for+gui+agents%2E+arXiv+preprint+arXiv%3A2403%2E02713%2E)
69. Li Zhang, Longxi Gao, and Mengwei Xu. 2025d. Does chain-of-thought reasoning help mobile gui agent? an empirical study. arXiv preprint arXiv:2503.16788. — [arXiv:2503.16788](https://arxiv.org/abs/2503.16788) [find](https://scholar.google.com/scholar?q=Li+Zhang%2C+Longxi+Gao%2C+and+Mengwei+Xu%2E+2025d%2E+Does+chain%2Dof%2Dthought+reasoning+help+mobile+gui+agent%3F+an+empirical+study%2E+arXiv+preprint+arXiv%3A2503%2E16788%2E+%E2%80%94+%5BarXiv%3A2503%2E16788%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503)
70. Di Zhao, Longhui Ma, Siwei Wang, Miao Wang, and Zhao Lv. 2025. Cola: A scalable multi-agent framework for windows ui task automation. arXiv preprint arXiv:2503.09263. — [arXiv:2503.09263](https://arxiv.org/abs/2503.09263) [find](https://scholar.google.com/scholar?q=Di+Zhao%2C+Longhui+Ma%2C+Siwei+Wang%2C+Miao+Wang%2C+and+Zhao+Lv%2E+2025%2E+Cola%3A+A+scalable+multi%2Dagent+framework+for+windows+ui+task+automation%2E+arXiv+preprint+arXiv%3A2503%2E09263%2E+%E2%80%94+%5BarXiv%3A2503%2E09263%5D%28https%3A%2F%2Farxi)
71. Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, and 1 others. 2023. [Webarena: A realistic web environment for building autonomous agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/). arXiv preprint arXiv:2307.13854.
72. Yuqi Zhou, Sunhao Dai, Shuai Wang, Kaiwen Zhou, Qinglin Jia, and Jun Xu. 2025. Gui-g1: Understanding r1-zero-like training for visual grounding in gui agents. arXiv preprint arXiv:2505.15810. — [arXiv:2505.15810](https://arxiv.org/abs/2505.15810) [find](https://scholar.google.com/scholar?q=Yuqi+Zhou%2C+Sunhao+Dai%2C+Shuai+Wang%2C+Kaiwen+Zhou%2C+Qinglin+Jia%2C+and+Jun+Xu%2E+2025%2E+Gui%2Dg1%3A+Understanding+r1%2Dzero%2Dlike+training+for+visual+grounding+in+gui+agents%2E+arXiv+preprint+arXiv%3A2505%2E15810%2E+%E2%80%94+%5BarXiv)

*Updated 2 November 2026*