{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:47Z","timestamp":1776931187406,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3790396","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:14:30Z","timestamp":1776057270000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DroidRetriever: A Transparent and Steerable Automation System for Collaborative Mobile Information Seeking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8628-1751","authenticated-orcid":false,"given":"Yiheng","family":"Bian","sequence":"first","affiliation":[{"name":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-0408","authenticated-orcid":false,"given":"Yunpeng","family":"Song","sequence":"additional","affiliation":[{"name":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9910-5301","authenticated-orcid":false,"given":"Guiyu","family":"Ma","sequence":"additional","affiliation":[{"name":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3181-9445","authenticated-orcid":false,"given":"Rongrong","family":"Zhu","sequence":"additional","affiliation":[{"name":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4903-3992","authenticated-orcid":false,"given":"Zhongmin","family":"Cai","sequence":"additional","affiliation":[{"name":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Saaket Agashe Kyle Wong Vincent Tu Jiachen Yang Ang Li and Xin\u00a0Eric Wang. 2025. Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents. arxiv:https:\/\/arXiv.org\/abs\/2504.00906\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2504.00906"},{"key":"e_1_3_3_3_3_2","unstructured":"Qihang Ai Pi Bu Yue Cao Yingyao Wang Jihao Gu Jingxuan Xing Zekun Zhu Wei Jiang Zhicheng Zheng Jun Song Yuning Jiang and Bo Zheng. 2025. InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning. arxiv:https:\/\/arXiv.org\/abs\/2508.19679\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2508.19679"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_3_3_5_2","unstructured":"anthropic. 2024. Build with Claude - Computer use (beta). https:\/\/docs.anthropic.com\/en\/docs\/build-with-claude\/computer-use"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Jaime Arguello and Rob Capra. 2016. The Effects of Aggregated Search Coherence on Search Behavior. ACM Trans. Inf. Syst. 35 1 Article 2 (Sept. 2016) 30\u00a0pages. 10.1145\/2935747","DOI":"10.1145\/2935747"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/339"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830629.2835217"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984538"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126651"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Weiwei Gao Kexin Du Yujia Luo Weinan Shi Chun Yu and Yuanchun Shi. 2024. EasyAsk: An In-App Contextual Tutorial Search Assistant for Older Adults with Voice and Touch Inputs. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 8 3 (2024) 1\u201327.","DOI":"10.1145\/3678516"},{"key":"e_1_3_3_3_12_2","unstructured":"Genspark. 2024. Welcome to Genspark the AI Agent Engine. https:\/\/mainfunc.ai\/blog\/genspark_intro"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984557"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173825"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Nina Hollender Cristian Hofmann Michael Deneke and Bernhard Schmitz. 2010. Integrating cognitive load theory and concepts of human\u2013computer interaction. Computers in Human Behavior 26 6 (2010) 1278\u20131288. 10.1016\/j.chb.2010.05.031Online Interactivity: Role of Technology in Behavior Change.","DOI":"10.1016\/j.chb.2010.05.031"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642820"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_3_19_2","volume-title":"An Open Source Evaluation for Search APIs","author":"Akhilesh\u00a0Sharma Mehul\u00a0Chadda Ishaan,","year":"2024","unstructured":"Mehul\u00a0Chadda Ishaan, Akhilesh\u00a0Sharma. 2024. An Open Source Evaluation for Search APIs. https:\/\/github.com\/lumina-ai-inc\/benchmark"},{"key":"e_1_3_3_3_20_2","unstructured":"ItzCrazyKns. 2025. Perplexica: A privacy-focused AI answering engine. GitHub repository. https:\/\/github.com\/ItzCrazyKns\/Perplexica Version 1.9.1."},{"key":"e_1_3_3_3_21_2","volume-title":"YOLO by Ultralytics","author":"Jocher Glenn","year":"2023","unstructured":"Glenn Jocher, Ayush Chaurasia, and Jing Qiu. 2023. YOLO by Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642059"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713813"},{"key":"e_1_3_3_3_24_2","unstructured":"Kai. 2024. Unleash AI Search Power with Devv.AI: A Developer\u2019s Guide. https:\/\/devv.ai\/blog\/post\/devvai-devs-search-guide"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753631"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124878"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642874"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2678025.2701399"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609631"},{"key":"e_1_3_3_3_30_2","unstructured":"Jungjae Lee Dongjae Lee Chihun Choi Youngmin Im Jaeyoung Wi Kihong Heo Sangeun Oh Sunjae Lee and Insik Shin. 2025. Safeguarding Mobile GUI Agent via Logic-based Action Verification. arxiv:https:\/\/arXiv.org\/abs\/2503.18492\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2503.18492"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"John\u00a0D. Lee and Katrina\u00a0A. See. 2004. Trust in Automation: Designing for Appropriate Reliance. Human Factors 46 1 (2004) 50\u201380. 10.1518\/hfes.46.1.50_30392PMID: 15151155.","DOI":"10.1518\/hfes.46.1.50_30392"},{"key":"e_1_3_3_3_32_2","unstructured":"Sunjae Lee Junyoung Choi Jungjae Lee Munim\u00a0Hasan Wasi Hojun Choi Steven\u00a0Y. Ko Sangeun Oh and Insik Shin. 2024. Explore Select Derive and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation. arxiv:https:\/\/arXiv.org\/abs\/2312.03003\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2312.03003"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598076"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","unstructured":"Toby Jia-Jun Li Jingya Chen Brandon Canfield and Brad\u00a0A. Myers. 2020. Privacy-Preserving Script Sharing in GUI-based Programming-by-Demonstration Systems. Proc. ACM Hum.-Comput. Interact. 4 CSCW1 Article 60 (May 2020) 23\u00a0pages. 10.1145\/3392869","DOI":"10.1145\/3392869"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415820"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Shaobo Liang and Ziyi Wei. 2024. Understanding Users\u2019 App-Switching Behavior During the Mobile Search: An Empirical Study from the Perspective of Push\u2013Pull\u2013Mooring Framework. Behavioral Sciences 14 11 (2024). 10.3390\/bs14110989","DOI":"10.3390\/bs14110989"},{"key":"e_1_3_3_3_37_2","unstructured":"Yuwen Lu Meng Chen Qi Zhao Victor Cox Yang Yang Meng Jiang Jay Brockman Tamara Kay and Toby Jia-Jun Li. 2025. Crepe: A Mobile Screen Data Collector Using Graph Query. arxiv:https:\/\/arXiv.org\/abs\/2406.16173\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2406.16173"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210060"},{"key":"e_1_3_3_3_39_2","volume-title":"Morphic","author":"Miura Yoshiki","year":"2024","unstructured":"Yoshiki Miura. 2024. Morphic. https:\/\/github.com\/miurla\/morphic"},{"key":"e_1_3_3_3_40_2","volume-title":"ChatGPT Retrieval Plugin","year":"2023","unstructured":"OpenAI. 2023. ChatGPT Retrieval Plugin. https:\/\/github.com\/openai\/chatgpt-retrieval-plugin"},{"key":"e_1_3_3_3_41_2","unstructured":"OpenAI. 2024. SearchGPT Prototype. https:\/\/openai.com\/index\/searchgpt-prototype\/"},{"key":"e_1_3_3_3_42_2","unstructured":"OpenAI. 2025. Introducing Operator \u2014 an AI agent that can use a computer for you. https:\/\/openai.com\/index\/introducing-operator\/."},{"key":"e_1_3_3_3_43_2","unstructured":"Yi-Hao Peng Dingzeyu Li Jeffrey\u00a0P. Bigham and Amy Pavel. 2025. Morae: Proactively Pausing UI Agents for User Choices. arxiv:https:\/\/arXiv.org\/abs\/2508.21456\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2508.21456"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/223904.223911"},{"key":"e_1_3_3_3_45_2","volume-title":"Conference: Proceedings of International Conference on Intelligence Analysis","author":"Pirolli Peter","year":"2005","unstructured":"Peter Pirolli and Stuart Card. 2005. The sensemaking process and leverage points for analyst technology as identified through cognitive task analysis. In Conference: Proceedings of International Conference on Intelligence Analysis."},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"crossref","unstructured":"Laura\u00a0Pope Robbins Lisa Esposito Chris Kretz and Michael Aloi. 2007. What a user wants: Redesigning a library\u2019s web site based on a card-sort analysis. Journal of Web Librarianship 1 4 (2007) 3\u201327.","DOI":"10.1080\/19322900802111346"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0148"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290620"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","unstructured":"Christina Siu and Barbara\u00a0S. Chaparro. 2014. First Look: Examining the Horizontal Grid Layout using Eye-tracking. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 58 1 (2014) 1119\u20131123. arXiv:10.1177\/154193121458123410.1177\/1541931214581234","DOI":"10.1177\/1541931214581234"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676386"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676356"},{"key":"e_1_3_3_3_52_2","unstructured":"Wanderboat. [n. d.]. Your everyday Al companion for getaway ideas. https:\/\/wanderboat.ai\/about"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580895"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474765"},{"key":"e_1_3_3_3_55_2","unstructured":"Junyang Wang Haiyang Xu Haitao Jia Xi Zhang Ming Yan Weizhou Shen Ji Zhang Fei Huang and Jitao Sang. 2024. Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01014 (2024)."},{"key":"e_1_3_3_3_56_2","unstructured":"Junyang Wang Haiyang Xu Jiabo Ye Ming Yan Weizhou Shen Ji Zhang Fei Huang and Jitao Sang. 2024. Mobile-agent: Autonomous multi-modal mobile device agent with visual perception. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.16158 (2024)."},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649379"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581197"},{"key":"e_1_3_3_3_59_2","unstructured":"An Yan Zhengyuan Yang Wanrong Zhu Kevin Lin Linjie Li Jianfeng Wang Jianwei Yang Yiwu Zhong Julian McAuley Jianfeng Gao et\u00a0al. 2023. Gpt-4v in wonderland: Large multimodal models for zero-shot smartphone gui navigation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.07562 (2023)."},{"key":"e_1_3_3_3_60_2","volume-title":"Search with Lepton","author":"Yangqing\u00a0Jia Yadong\u00a0Xie","year":"2024","unstructured":"Yadong\u00a0Xie Yangqing\u00a0Jia. 2024. Search with Lepton. https:\/\/github.com\/leptonai\/search_with_lepton"},{"key":"e_1_3_3_3_61_2","unstructured":"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. arxiv:https:\/\/arXiv.org\/abs\/2508.15144\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2508.15144"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"crossref","unstructured":"Keen You Haotian Zhang Eldon Schoop Floris Weers Amanda Swearngin Jeffrey Nichols Yinfei Yang and Zhe Gan. 2024. Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.05719 (2024).","DOI":"10.1007\/978-3-031-73039-9_14"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/2212776.2212463"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642796"},{"key":"e_1_3_3_3_65_2","unstructured":"Chi Zhang Zhao Yang Jiaxuan Liu Yucheng Han Xin Chen Zebiao Huang Bin Fu and Gang Yu. 2023. AppAgent: Multimodal Agents as Smartphone Users. arxiv:https:\/\/arXiv.org\/abs\/2312.13771\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2312.13771"},{"key":"e_1_3_3_3_66_2","volume-title":"SenseVoice","author":"Lizerui9926 Shi\u00a0Xian zhifu gao,","year":"2024","unstructured":"Shi\u00a0Xian zhifu gao, Lizerui9926. 2024. SenseVoice. https:\/\/github.com\/FunAudioLLM\/SenseVoice"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.187"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T09:44:35Z","timestamp":1776419075000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3790396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":66,"alternative-id":["10.1145\/3772318.3790396","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3790396","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}