Teach-and-Repeat: Accurately Extracting Operational Knowledge from Mobile Screen Demonstrations to Empower GUI Agents

Computer Science > Artificial Intelligence [Submitted on 11 Jun 2026] Teach-and-Repeat: Accurately Extracting Operational Knowledge from Mobile Screen Demonstrations to Empower GUI Agents Yudong Zhang (1), Lei Hu (1), Daoyang Liu (2), Jiawei Liu (1), Yangfan Luo (1), Xingyu Liu (1), Zuojian Wang (1), Zhilin Gao (1) ((1) Honor Device Co., Ltd, (2) The Chinese University of Hong Kong, Hong Kong, China) Understanding the digital world on mobile devices is shifting from static UI perception to dynamic action comprehension. This capability enables models to convert visual state transitions into operational knowledge, defined as short natural-language sentences that describe action types, target UI elements, textual arguments, and execution orders. However, due to the highly diverse and heterogeneous UI designs across applications, existing vision-language models (VLMs) struggle to accurately infer these underlying operations. To bridge this gap, we introduce Teach VLM, a core model designed to translate mobile screen trajectories into step-wise operational knowledge by extracting and analyzing operation-related keyframes from demonstration videos. To address the scarcity of aligned training data, we develop a systematic data flywheel for scalable data acquisition. We further introduce a novel Chinese Mobile Screen Teach Benchmark for fine-grained evaluation. Building upon Teach VLM, we propose the Teach-and-Repeat paradigm, where the generated operational knowledge serves as an interpretable procedural reference to guide downstream screen-based execution agents. Extensive evaluations demonstrate that Teach VLM significantly outperforms strong VLM baselines, achieving state-of-the-art performance in operation semantics prediction. Furthermore, experiments in Android World show that our paradigm yields consistent Task Success Rate improvements for downstream agents. Together, Teach VLM and the Teach-and-Repeat paradigm offer a practical pathway from raw demonstrations to reusable task automation. Comments: 20 pages, 9 figures. Yudong Zhang and Lei Hu contributed equally to this work. Xingyu Liu, Zuojian Wang, and Zhilin Gao are corresponding authors Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.12817 [cs.AI]   (or arXiv:2606.12817v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.12817 Focus to learn more Submission history From: Yudong Zhang [view email] [v1] Thu, 11 Jun 2026 02:24:39 UTC (19,344 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)