{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T07:59:11Z","timestamp":1780473551137,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00347516"],"award-info":[{"award-number":["RS-2024-00347516"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,4]]},"DOI":"10.1145\/3636534.3690682","type":"proceedings-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T23:13:18Z","timestamp":1733353998000},"page":"1119-1133","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["MobileGPT: Augmenting LLM with Human-like App Memory for Mobile Task Automation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2755-5511","authenticated-orcid":false,"given":"Sunjae","family":"Lee","sequence":"first","affiliation":[{"name":"School of Computing, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3357-2710","authenticated-orcid":false,"given":"Junyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9235-5900","authenticated-orcid":false,"given":"Jungjae","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9662-3146","authenticated-orcid":false,"given":"Munim Hasan","family":"Wasi","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4121-4519","authenticated-orcid":false,"given":"Hojun","family":"Choi","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3771-0156","authenticated-orcid":false,"given":"Steve","family":"Ko","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2294-6572","authenticated-orcid":false,"given":"Sangeun","family":"Oh","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9128-2415","authenticated-orcid":false,"given":"Insik","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Daejeon, Republic of Korea"},{"name":"Fluiz, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Retrieved","year":"2023","unstructured":"anthropic. 2023. Talk to Claude. anthropic. Retrieved Nov 11, 2023 from https:\/\/claude.ai\/"},{"key":"e_1_3_2_1_2_1","volume-title":"Meta. Retrieved","year":"2023","unstructured":"Apple. 2023. Use Siri on all your Apple devices. Meta. Retrieved Nov 11, 2023 from https:\/\/support.apple.com\/en-us\/HT204389"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2835587.2835589"},{"key":"e_1_3_2_1_4_1","volume-title":"Sus: a \"quick and dirty' usability. Usability evaluation in industry 189, 3","author":"Brooke John","year":"1996","unstructured":"John Brooke. 1996. Sus: a \"quick and dirty' usability. Usability evaluation in industry 189, 3 (1996), 189--194."},{"key":"e_1_3_2_1_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011087"},{"key":"e_1_3_2_1_7_1","volume-title":"Resource-rational task decomposition to minimize planning costs. arXiv preprint arXiv:2007.13862","author":"Correa Carlos G","year":"2020","unstructured":"Carlos G Correa, Mark K Ho, Fred Callaway, and Thomas L Griffiths. 2020. Resource-rational task decomposition to minimize planning costs. arXiv preprint arXiv:2007.13862 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.17679\/inuefd.597890"},{"key":"e_1_3_2_1_9_1","volume-title":"Prompt cache: Modular attention reuse for low-latency inference. arXiv preprint arXiv:2311.04934","author":"Gim In","year":"2023","unstructured":"In Gim, Guojun Chen, Seung-seob Lee, Nikhil Sarda, Anurag Khandelwal, and Lin Zhong. 2023. Prompt cache: Modular attention reuse for low-latency inference. arXiv preprint arXiv:2311.04934 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Google. Retrieved","year":"2023","unstructured":"Google. 2023. Create your own accessibility service. Google. Retrieved Nov 11, 2023 from https:\/\/developer.android.com\/guide\/topics\/ui\/accessibility\/service"},{"key":"e_1_3_2_1_11_1","volume-title":"Google. Retrieved","year":"2023","unstructured":"Google. 2023. Hey Google. Google. Retrieved Nov 11, 2023 from https:\/\/assistant.google.com\/"},{"key":"e_1_3_2_1_12_1","volume-title":"Google. Retrieved","year":"2024","unstructured":"Google. 2024. Profile your app performance. Google. Retrieved July 25, 2024 from https:\/\/developer.android.com\/studio\/profile\/"},{"key":"e_1_3_2_1_13_1","volume-title":"Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738","author":"Gou Zhibin","year":"2023","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2023. Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Gregersen","author":"Emilie Munch","year":"2023","unstructured":"Emilie Munch et al Gregersen. 2023. Digital dependence: Online fatigue and coping strategies during the COVID-19 lockdown. Media, Culture, and Society (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"How do users like this feature? a fine grained sentiment analysis of app reviews. In 2014 IEEE 22nd international requirements engineering conference (RE). Ieee, 153--162","author":"Guzman Emitza","unstructured":"Emitza Guzman and Walid Maalej. 2014. How do users like this feature? a fine grained sentiment analysis of app reviews. In 2014 IEEE 22nd international requirements engineering conference (RE). Ieee, 153--162."},{"key":"e_1_3_2_1_16_1","volume-title":"Automatic Macro Mining from Interaction Traces at Scale. arXiv preprint arXiv:2310.07023","author":"Huang Forrest","year":"2023","unstructured":"Forrest Huang, Gang Li, Tao Li, and Yang Li. 2023. Automatic Macro Mining from Interaction Traces at Scale. arXiv preprint arXiv:2310.07023 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. PMLR, 9466--9482","author":"Humphreys Peter C","year":"2022","unstructured":"Peter C Humphreys, David Raposo, Tobias Pohlen, Gregory Thornton, Rachita Chhaparia, Alistair Muldal, Josh Abramson, Petko Georgiev, Adam Santoro, and Timothy Lillicrap. 2022. A data-driven approach for learning to control computers. In International Conference on Machine Learning. PMLR, 9466--9482."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning. PMLR, 9466--9482","author":"Humphreys Peter C","year":"2022","unstructured":"Peter C Humphreys, David Raposo, Tobias Pohlen, Gregory Thornton, Rachita Chhaparia, Alistair Muldal, Josh Abramson, Petko Georgiev, Adam Santoro, and Timothy Lillicrap. 2022. A data-driven approach for learning to control computers. In International Conference on Machine Learning. PMLR, 9466--9482."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Akshay Kumar Jagadish Marcel Binz Tankred Saanum Jane X Wang and Eric Schulz. 2023. Zero-shot compositional reinforcement learning in humans. (2023).","DOI":"10.31234\/osf.io\/ymve5"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2805837"},{"key":"e_1_3_2_1_21_1","unstructured":"Kenton Lee Mandar Joshi Iulia Turc Hexiang Hu Fangyu Liu Julian Eisenschlos Urvashi Khandelwal Peter Shaw Ming-Wei Chang and Kristina Toutanova. 2023. Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding. arXiv:2210.03347 [cs.CL]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560522"},{"key":"e_1_3_2_1_23_1","volume-title":"Spotlight: Mobile UI understanding using vision-language models with a focus.","author":"Li Gang","year":"2023","unstructured":"Gang Li and Yang Li. 2023. Spotlight: Mobile UI understanding using vision-language models with a focus. (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"MUG: Interactive Multimodal Grounding on User Interfaces. arXiv preprint arXiv:2209.15099","author":"Li Tao","year":"2022","unstructured":"Tao Li, Gang Li, Jingjie Zheng, Purple Wang, and Yang Li. 2022. MUG: Interactive Multimodal Grounding on User Interfaces. arXiv preprint arXiv:2209.15099 (2022)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025483"},{"key":"e_1_3_2_1_26_1","volume-title":"End-User Development: 6th International Symposium, IS-EUD 2017, Eindhoven, The Netherlands, June 13--15, 2017, Proceedings 6. Springer, 3--17","author":"Jia-Jun Li Toby","year":"2017","unstructured":"Toby Jia-Jun Li, Yuanchun Li, Fanglin Chen, and Brad A Myers. 2017. Programming IoT devices by demonstration using mobile apps. In End-User Development: 6th International Symposium, IS-EUD 2017, Eindhoven, The Netherlands, June 13--15, 2017, Proceedings 6. Springer, 3--17."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1--15","author":"Jia-Jun Li Toby","year":"2021","unstructured":"Toby Jia-Jun Li, Lindsay Popowski, Tom Mitchell, and Brad A Myers. 2021. Screen2vec: Semantic embedding of gui screens and gui components. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1--15."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services. 96--109","author":"Jia-Jun Li Toby","year":"2018","unstructured":"Toby Jia-Jun Li and Oriana Riva. 2018. KITE: Building conversational bots from mobile apps. In Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services. 96--109."},{"key":"e_1_3_2_1_29_1","volume-title":"Mapping natural language instructions to mobile UI action sequences. arXiv preprint arXiv:2005.03776","author":"Li Yang","year":"2020","unstructured":"Yang Li, Jiacong He, Xin Zhou, Yuan Zhang, and Jason Baldridge. 2020. Mapping natural language instructions to mobile UI action sequences. arXiv preprint arXiv:2005.03776 (2020)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462905"},{"key":"e_1_3_2_1_31_1","volume-title":"Visual instruction tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1049\/sfw2.12042"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2020.11.002"},{"key":"e_1_3_2_1_34_1","volume-title":"Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. 2023. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Retrieved","year":"2023","unstructured":"meta. 2023. Introducing Llama 2. meta. Retrieved Nov 11, 2023 from https:\/\/ai.meta.com\/llama\/"},{"key":"e_1_3_2_1_36_1","volume-title":"Microsoft. Retrieved","year":"2023","unstructured":"Microsoft. 2023. How to detect and redact Personally Identifying Information (PII). Microsoft. Retrieved Nov 11, 2023 from https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/language-service\/personally-identifiable-information\/how-to-call"},{"key":"e_1_3_2_1_37_1","volume-title":"Retrieved","year":"2024","unstructured":"mnotgod96. 2024. AppAgent-TencentQQGYLab. Retrieved July 25, 2024 from https:\/\/github.com\/mnotgod96\/AppAgent"},{"key":"e_1_3_2_1_38_1","volume-title":"Retrieved","author":"LLM.","year":"2024","unstructured":"MobileLLM. 2024. AutoDroid. Retrieved July 25, 2024 from https:\/\/gitfiub.com\/MobileLLM\/AutoDroid"},{"key":"e_1_3_2_1_39_1","volume-title":"MultiOn. Retrieved","year":"2023","unstructured":"MultiOn. 2023. The world's first Personal AI Agent. MultiOn. Retrieved Nov 11, 2023 from https:\/\/www.multion.ai\/"},{"key":"e_1_3_2_1_40_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2021","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Retrieved","year":"2023","unstructured":"openai. 2023. Creating safe AGI that benefits all of humanity. openai. Retrieved Nov 11, 2023 from https:\/\/openai.com\/"},{"key":"e_1_3_2_1_42_1","volume-title":"OpenAI. Retrieved","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. New and improved embedding model. OpenAI. Retrieved Nov 11, 2023 from https:\/\/openai.com\/blog\/new-and-improved-embedding-model"},{"key":"e_1_3_2_1_43_1","volume-title":"OpenAI. Retrieved","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. Vision. OpenAI. Retrieved Nov 11, 2023 from https:\/\/platform.openai.com\/docs\/guides\/vision"},{"key":"e_1_3_2_1_44_1","volume-title":"OthersideAI. Retrieved","author":"AI.","year":"2023","unstructured":"OthersideAI. 2023. Your AI assistant for everyday tasks. OthersideAI. Retrieved Nov 11, 2023 from https:\/\/www.hyperwriteai.com\/personal-assistant"},{"key":"e_1_3_2_1_45_1","volume-title":"Pinecone Systems. Retrieved","year":"2023","unstructured":"Pinecone. 2023. Long-Term Memory for AI. Pinecone Systems. Retrieved Nov 11, 2023 from https:\/\/www.pinecone.io\/"},{"key":"e_1_3_2_1_46_1","volume-title":"Endpoint Protector. Retrieved","author":"Protector Endpoint","year":"2023","unstructured":"Endpoint Protector. 2023. Cutting-Edge PII Scanner. Endpoint Protector. Retrieved Nov 11, 2023 from https:\/\/www.endpointprotector.com\/solutions\/ediscovery\/pii-scanner"},{"key":"e_1_3_2_1_47_1","volume-title":"Optimising API calls to large language models. arXiv preprint arXiv:2310.13561","author":"Ram\u00edrez Guillem","year":"2023","unstructured":"Guillem Ram\u00edrez, Matthias Lindemann, Alexandra Birch, and Ivan Titov. 2023. Cache & distil: Optimising API calls to large language models. arXiv preprint arXiv:2310.13561 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Android in the wild: A large-scale dataset for android device control. arXiv preprint arXiv:2307.10088","author":"Rawles Christopher","year":"2023","unstructured":"Christopher Rawles, Alice Li, Daniel Rodriguez, Oriana Riva, and Timothy Lillicrap. 2023. Android in the wild: A large-scale dataset for android device control. arXiv preprint arXiv:2307.10088 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Retrieved","year":"2023","unstructured":"Significant-Gravitas. 2023. AutoGPT: the heart of the open-source agent ecosystem. github. Retrieved Nov 11, 2023 from https:\/\/github.com\/Significant-Gravitas\/AutoGPT"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/RE48521.2020.00019"},{"key":"e_1_3_2_1_51_1","volume-title":"Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models. arXiv preprint arXiv:2310.13395","author":"Stogiannidis Ilias","year":"2023","unstructured":"Ilias Stogiannidis, Stavros Vassos, Prodromos Malakasiotis, and Ion Androutsopoulos. 2023. Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models. arXiv preprint arXiv:2310.13395 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI. arXiv preprint arXiv:2205.11029","author":"Sun Liangtai","year":"2022","unstructured":"Liangtai Sun, Xingyu Chen, Lu Chen, Tianle Dai, Zichen Zhu, and Kai Yu. 2022. META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI. arXiv preprint arXiv:2205.11029 (2022)."},{"key":"e_1_3_2_1_53_1","volume-title":"Androidenv: A reinforcement learning platform for android. arXiv preprint arXiv:2105.13231","author":"Toyama Daniel","year":"2021","unstructured":"Daniel Toyama, Philippe Hamel, Anita Gergely, Gheorghe Comanici, Amelia Glaese, Zafarali Ahmed, Tyler Jackson, Shibl Mourad, and Doina Precup. 2021. Androidenv: A reinforcement learning platform for android. arXiv preprint arXiv:2105.13231 (2021)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580895"},{"key":"e_1_3_2_1_55_1","volume-title":"Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291","author":"Wang Guanzhi","year":"2023","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Roy Ka-Wei Lee, and Ee-Peng Lim","author":"Wang Lei","year":"2023","unstructured":"Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. 2023. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. arXiv preprint arXiv:2305.11175","author":"Wang Wenhai","year":"2023","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2023. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. arXiv preprint arXiv:2305.11175 (2023)."},{"key":"e_1_3_2_1_58_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824--24837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","volume-title":"Shiqi Jiang, Yunhao Liu, Yaqin Zhang, and Yunxin Liu.","author":"Wen Hao","year":"2023","unstructured":"Hao Wen, Yuanchun Li, Guohong Liu, Shanhui Zhao, Tao Yu, Toby Jia-Jun Li, Shiqi Jiang, Yunhao Liu, Yaqin Zhang, and Yunxin Liu. 2023. Empowering llm to use smartphone for intelligent task automation. arXiv preprint arXiv:2308.15272 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"DroidBot-GPT: GPT-powered UI Automation for Android. arXiv preprint arXiv:2304.07061","author":"Wen Hao","year":"2023","unstructured":"Hao Wen, Hongming Wang, Jiaxuan Liu, and Yuanchun Li. 2023. DroidBot-GPT: GPT-powered UI Automation for Android. arXiv preprint arXiv:2304.07061 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581158"},{"key":"e_1_3_2_1_62_1","volume-title":"Appagent: Multimodal agents as smartphone users. arXiv preprint arXiv:2312.13771","author":"Yang Zhao","year":"2023","unstructured":"Zhao Yang, Jiaxuan Liu, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, and Gang Yu. 2023. Appagent: Multimodal agents as smartphone users. arXiv preprint arXiv:2312.13771 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"},{"key":"e_1_3_2_1_64_1","volume-title":"Efficient Prompt Caching via Embedding Similarity. arXiv preprint arXiv:2402.01173","author":"Zhu Hanlin","year":"2024","unstructured":"Hanlin Zhu, Banghua Zhu, and Jiantao Jiao. 2024. Efficient Prompt Caching via Embedding Similarity. arXiv preprint arXiv:2402.01173 (2024)."}],"event":{"name":"ACM MobiCom '24: 30th Annual International Conference on Mobile Computing and Networking","location":"Washington D.C. DC USA","acronym":"ACM MobiCom '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 30th Annual International Conference on Mobile Computing and Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3690682","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3636534.3690682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:36Z","timestamp":1750295856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3690682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"references-count":64,"alternative-id":["10.1145\/3636534.3690682","10.1145\/3636534"],"URL":"https:\/\/doi.org\/10.1145\/3636534.3690682","relation":{},"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"2024-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}