Elamur Research⌕
☰
home / papers / 2026 / GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems

GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems

Paper · 2026 · Xinyi Wang, Wei Dai, Kyle Qiao et al.

Summary

GUI agents struggle inside Super Apps such as WeChat. These platforms host many mini apps that are often rendered through Canvas or WebViews, and they frequently lack accessibility metadata. An agent must therefore read the interface from raw pixels and plan long action sequences with little feedback. The authors propose GUI0 to address this.

An Action Tracker explores mini apps with random walks and DFS, and the logged trajectories are labelled with instructions after the fact. The resulting corpus is checked by a VLM filter and then by human reviewers. It feeds continual pre-training, which builds a domain-aware foundation model. An actor agent is then refined with SFT and GRPO. A separate curriculum agent co-evolves with the actor, proposing tasks that sit just at the edge of what the actor can currently do.

On the new SuperAPP benchmark, GUI0 outperforms Gemini-2.5-Pro and Claude-4-Sonnet. It also generalizes zero-shot to standard GUI benchmarks. The work matters because it offers a way to automate non-standard app ecosystems without manual annotation.

Key points

  • SuperAPP benchmark: 230 tasks drawn from real user queries, covering 172 mini apps in 6 categories. Commerce & Local Services is the largest category at 26.5%. Tasks were validated by a ten-person expert team and run on Android emulators.
  • Main result: peak success rate of 68.7%, which is +24.3% over Gemini-2.5-Pro and +44.8% over the backbone model. The paper also reports a +62.7% gain on ScreenSpot Pro.
  • Synthetic corpus: annotated with Gemini-2.5-Pro and organized into five task types:
    • GUI state transitions (forward and inverse dynamics)
    • dense screen descriptions
    • multi-turn grounding VQA
    • reflective reasoning
    • trajectory CoT
  • Generality: gains hold across Qwen2.5-VL and GUI-Owl base models. The agent uses a 10-operation action space, with coordinates derived from OmniParser bounding boxes.
  • Limitations: one Qwen2.5-VL judge handles both rewards and evaluation, which risks reward hacking. Comparisons with closed models may be uneven, and some negative transfer appears on AndroidWorld.

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

🏢TencentShenzhen · China134 works · 19,743 citations🎓Renmin University of ChinaBeijing · China114 works · 16,118 citations🎓Zhejiang UniversityHangzhou · China172 works · 12,988 citations🎓Beijing University of Posts and TelecommunicationsBeijing · China57 works · 32,843 citations🎓University of Chinese Academy of SciencesBeijing · China147 works · 8,480 citations🎓Nankai UniversityTianjin · China24 works · 762 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 worksHuman-Computer Interaction · 141 works

Cite

Cite as Xinyi Wang, Wei Dai, Kyle Qiao, Ke Wang, Peng Chen, Gang Cao, Kangqin, Zhongpu Wang, Xiaode Zhang, Yanming Liu, Jihao Gu, Jingtao Xu and Gong Zhi. 2026. GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems. 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.2052

@inproceedings{wang2026gui0,
  title = {{GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems}},
  author = {Xinyi Wang, Wei Dai, Kyle Qiao, Ke Wang, Peng Chen, Gang Cao, Kangqin, Zhongpu Wang, Xiaode Zhang, Yanming Liu, Jihao Gu, Jingtao Xu and Gong Zhi},
  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.2052},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2052}
}

References

41 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  2. Wei Chen, Zhiyuan Li, and Mingyuan Ma. 2025a. Octopus: On-device language model for function calling of software apis. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)… find
  3. Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, and 1 others. 2025b. Guicourse: From general vision language model to versatile gui agent. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics… find
  4. 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. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9313–9332.
  5. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  6. Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang, Xinhao Yi, Guibin Zhang, Yi Xu, Bin Wu, Siwei Liu, Zihao Li, and 1 others. 2025. A comprehensive survey of self-evolving ai agents: A new paradigm bridging foundation models and lifelong agentic systems. arXiv preprint arXiv:2508.07407. — [arXiv:2508.07407](https://arxiv.org/abs/2508.07407) find
  7. Huan-ang Gao, Jiayi Geng, Wenyue Hua, Mengkang Hu, Xinzhe Juan, Hongzhang Liu, Shilong Liu, Jiahao Qiu, Xuan Qi, Yiran Wu, and 1 others. 2025. A survey of self-evolving agents: On path to artificial super intelligence. arXiv preprint arXiv:2507.21046. find
  8. Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, and 1 others. 2025a. Mobile-r1: Towards interactive reinforcement learning for vlm-based mobile agent via task-level rewards. arXiv preprint arXiv:2506.20332. — [arXiv:2506.20332](https://arxiv.org/abs/2506.20332) find
  9. Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, and 1 others. 2025b. Ui-venus technical report: Building high-performance ui agents with rft. arXiv preprint arXiv:2508.10833. — [arXiv:2508.10833](https://arxiv.org/abs/2508.10833) find
  10. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  11. Wenjia Jiang, Yangyang Zhuang, Chenxi Song, Xu Yang, Joey Tianyi Zhou, and Chi Zhang. 2025. Appagentx: Evolving gui agents as proficient smartphone users. arXiv preprint arXiv:2503.02268. — [arXiv:2503.02268](https://arxiv.org/abs/2503.02268) find
  12. Hongxin Li, Jingran Su, Jingfan Chen, Zheng Ju, Yuntao Chen, Qing Li, and Zhaoxiang Zhang. 2025a. Uipro: Unleashing superior interaction capability for gui agents. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1613–1623. find
  13. Jiahao Li and Kaer Huang. 2025. A survey on gui agents with foundation models enhanced by reinforcement learning. arXiv preprint arXiv:2504.20464. — [arXiv:2504.20464](https://arxiv.org/abs/2504.20464) find
  14. Kaixin Li, Ziyang Meng, Hongzhan Lin, Ziyang Luo, Yuchen Tian, Jing Ma, Zhiyong Huang, and Tat-Seng Chua. 2025b. Screenspot-pro: Gui grounding for professional high-resolution computer use. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 8778–8786. find
  15. 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. Advances in Neural Information Processing Systems, 37:92130–92154. find
  16. Wei Li, Borui Yang, Hangyu Ye, Liyao Xiang, Qingxiao Tao, Xinbing Wang, and Chenghu Zhou. 2024b. Minitracker: Large-scale sensitive information tracking in mini apps. IEEE Transactions on Dependable and Secure Computing, 21(4):2099–2114. find
  17. Yanda Li, Chi Zhang, Wenjia Jiang, Wanqi Yang, Bin Fu, Pei Cheng, Xin Chen, Ling Chen, and Yunchao Wei. 2024c. Appagent v2: Advanced agent for flexible mobile interactions. arXiv preprint arXiv:2408.11824. — [arXiv:2408.11824](https://arxiv.org/abs/2408.11824) find
  18. Kevin Qinghong Lin, Linjie Li, Difei Gao, Zhengyuan Yang, Shiwei Wu, Zechen Bai, Stan Weixian Lei, Lijuan Wang, and Mike Zheng Shou. 2025. Showui: One vision-language-action model for gui visual agent. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 19498– 19508. find
  19. Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, and Huaxiu Yao. 2025. Agent0-vl: Exploring self-evolving agent for tool-integrated vision-language reasoning. arXiv preprint arXiv:2511.19900. — [arXiv:2511.19900](https://arxiv.org/abs/2511.19900) find
  20. Yadong Lu, Jianwei Yang, Yelong Shen, and Ahmed Awadallah. 2024. Omniparser for pure vision based gui agent. arXiv preprint arXiv:2408.00203. — [arXiv:2408.00203](https://arxiv.org/abs/2408.00203) find
  21. Songqin Nong, Jingxuan Xu, Sheng Zhou, Jianfeng Chen, Xiaoxuan Tang, Tao Jiang, and Wenhao Xu. 2025. Craft-gui: Curriculum-reinforced agent for gui tasks. arXiv preprint arXiv:2508.11360. — [arXiv:2508.11360](https://arxiv.org/abs/2508.11360) find
  22. Jupinder Parmar, Sanjev Satheesh, Mostofa Patwary, Mohammad Shoeybi, and Bryan Catanzaro. 2024. Reuse, don’t retrain: A recipe for continued pre-training of language models. arXiv preprint arXiv:2407.07263.
  23. Yujia Qin, Yining Ye, Junjie Fang, Haoming Wang, Shihao Liang, Shizuo Tian, Junda Zhang, Jiahao Li, Yunxin Li, Shijue Huang, and 1 others. 2025. Ui-tars: Pioneering automated gui interaction with native agents. arXiv preprint arXiv:2501.12326.
  24. 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. arXiv preprint arXiv:2405.14573. find
  25. Yizhe Shi, Guangliang Yang, Zhemin Yang, Yifan Yang, Min Yang, Kangwei Zhong, and Xiaohan Zhang. 2025. The skeleton keys: A large scale analysis of credential leakage in mini-apps. find
  26. Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, and 1 others. 2025. Scaling agents via continual pre-training. arXiv preprint arXiv:2509.13310. — [arXiv:2509.13310](https://arxiv.org/abs/2509.13310) find
  27. Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, and Jiaqi Wang. 2025. Seagent: Self-evolving computer use agent with autonomous learning from experience. arXiv preprint arXiv:2508.04700. — [arXiv:2508.04700](https://arxiv.org/abs/2508.04700) find
  28. V Team, Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, Shuaiqi Duan, Weihan Wang, Yan Wang, Yean Cheng, Zehai He, Zhe Su, Zhen Yang, Ziyang Pan, and 69 others. 2025. Glm-4.5v and glm-4.1v-thinking: Towards versatile multimodal reas…
  29. Shenao Wang, Yuekang Li, Kailong Wang, Yi Liu, Hui Li, Yang Liu, and Haoyu Wang. 2025. Miniscope: Automated ui exploration and privacy inconsistency detection of miniapps via two-phase iterative hybrid analysis. ACM Transactions on Software Engineering and Methodology, 34(6):1–29. find
  30. Shuai Wang, Weiwen Liu, Jingxuan Chen, Yuqi Zhou, Weinan Gan, Xingshan Zeng, Yuhan Che, Shuai Yu, Xinlong Hao, Kun Shao, and 1 others. 2024. Gui agents with foundation models: A comprehensive survey. arXiv preprint arXiv:2411.04890. — [arXiv:2411.04890](https://arxiv.org/abs/2411.04890) find
  31. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. Self-instruct: Aligning language models with self-generated instructions. In Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long p… find
  32. Qinzhuo Wu, Weikai Xu, Wei Liu, Tao Tan, Liujian Liujianfeng, Ang Li, Jian Luan, Bin Wang, and Shuo Shang. 2024. Mobilevlm: A vision-language model for better intra-and inter-ui understanding. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10231–10251. find
  33. Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, and 1 others. 2025. Agentgym: Evaluating and training large language model-based agents across diverse environments. In Proceedings of the 63rd Annual Meeting of the Associatio… find
  34. Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, and Huaxiu Yao. 2025. Agent0: Unleashing self-evolving agents from zero data via tool-integrated reasoning. arXiv preprint arXiv:2511.16043. — [arXiv:2511.16043](https://arxiv.org/abs/2511.16043) find
  35. Tianbao Xie, Jiaqi Deng, Xiaochuan Li, Junlin Yang, Haoyuan Wu, Jixuan Chen, Wenjing Hu, Xinyuan Wang, Yuhui Xu, Zekun Wang, and 1 others. 2025. Scaling computer-use grounding via user interface decomposition and synthesis. arXiv preprint arXiv:2505.13227. find
  36. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2024. Wizardlm: Empowering large pre-trained language models to follow complex instructions. In The Twelfth International Conference on Learning Representations.
  37. Haolong Yan, Yeqing Shen, Xin Huang, Jia Wang, Kaijun Tan, Zhixuan Liang, Hongxin Li, Zheng Ge, Osamu Yoshie, Si Li, and 1 others. 2025. Gui exploration lab: Enhancing screen navigation in agents via multi-turn reinforcement learning. In The Thirty-ninth Annual Conference on Neural Information Proce… find
  38. 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: Fundamental agents for gui automation. arXiv preprint arXiv:2508.15144. — [arXiv:2508.15144](https://arxiv.org/abs/2508.15144) find
  39. Wenwen Yu, Zhibo Yang, Jianqiang Wan, Sibo Song, Jun Tang, Wenqing Cheng, Yuliang Liu, and Xiang Bai. 2025. Omniparser v2: Structured-points-of-thought for unified visual text parsing and its generality to multimodal large language models. arXiv preprint arXiv:2502.16161. — [arXiv:2502.16161](https://arxiv.org/abs/2502.16161) find
  40. Xinbin Yuan, Jian Zhang, Kaixin Li, Zhuoxuan Cai, Lujian Yao, Jie Chen, Enguang Wang, Qibin Hou, Jinwei Chen, Peng-Tao Jiang, and 1 others. 2025. Enhancing visual grounding for gui agents via self-evolutionary reinforcement learning. arXiv preprint arXiv:2505.12370. — [arXiv:2505.12370](https://arxiv.org/abs/2505.12370) find
  41. Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Guyue Liu, Qingwei Lin, and 1 others. 2024. Large language model-brained gui agents: A survey. arXiv preprint arXiv:2411.18279. — [arXiv:2411.18279](https://arxiv.org/abs/2411.18279) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-gui0-self-evolving-foundational-gui/