{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:19:13Z","timestamp":1783153153341,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"Shanghai Municipal Natural Science Foundation","award":["23ZR1425400"],"award-info":[{"award-number":["23ZR1425400"]}]},{"name":"Shanghai Soft Science Project","award":["25692114700"],"award-info":[{"award-number":["25692114700"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792257","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"5198-5209","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Curiosity Driven Knowledge Retrieval for Mobile Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0318-4276","authenticated-orcid":false,"given":"Sijia","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-7143","authenticated-orcid":false,"given":"Xiaoyu","family":"Tan","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3651-5654","authenticated-orcid":false,"given":"Shahir","family":"Ali","sequence":"additional","affiliation":[{"name":"Droidrun, Osnabr\u00fcck, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4950-6555","authenticated-orcid":false,"given":"Niels","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Droidrun, Osnabr\u00fcck, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3841-9889","authenticated-orcid":false,"given":"Gengchen","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4024-925X","authenticated-orcid":false,"given":"Xihe","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Agent s2: A compositional generalist-specialist framework for computer use agents. arXiv preprint arXiv:2504.00906","author":"Agashe Saaket","year":"2025","unstructured":"Saaket Agashe, Kyle Wong, Vincent Tu, Jiachen Yang, Ang Li, and Xin Eric Wang. 2025. Agent s2: A compositional generalist-specialist framework for computer use agents. arXiv preprint arXiv:2504.00906 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcpdig.2024.11.005"},{"key":"e_1_3_2_1_3_1","volume-title":"Appium: Cross-platform Mobile UI Automation Framework. https:\/\/github.com\/appium\/appium. Version: latest, Accessed: 2025-09-18.","author":"Contributors Appium","year":"2012","unstructured":"Appium Contributors. 2012. Appium: Cross-platform Mobile UI Automation Framework. https:\/\/github.com\/appium\/appium. Version: latest, Accessed: 2025-09-18."},{"key":"e_1_3_2_1_4_1","volume-title":"A Markovian decision process. Journal of mathematics and mechanics","author":"Bellman Richard","year":"1957","unstructured":"Richard Bellman. 1957. A Markovian decision process. Journal of mathematics and mechanics (1957), 679-684."},{"key":"e_1_3_2_1_5_1","volume-title":"Seeclick: Harnessing gui grounding for advanced visual gui agents. arXiv preprint arXiv:2401.10935","author":"Cheng Kanzhi","year":"2024","unstructured":"Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, and Zhiyong Wu. 2024. Seeclick: Harnessing gui grounding for advanced visual gui agents. arXiv preprint arXiv:2401.10935 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Advancing mobile gui agents: A verifier-driven approach to practical deployment. arXiv preprint arXiv:2503.15937","author":"Dai Gaole","year":"2025","unstructured":"Gaole Dai, Shiqi Jiang, Ting Cao, Yuanchun Li, Yuqing Yang, Rui Tan, Mo Li, and Lili Qiu. 2025a. Advancing mobile gui agents: A verifier-driven approach to practical deployment. arXiv preprint arXiv:2503.15937 (2025)."},{"key":"e_1_3_2_1_7_1","volume-title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models. arXiv preprint arXiv:2509.09675","author":"Dai Runpeng","year":"2025","unstructured":"Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, et al., 2025b. CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models. arXiv preprint arXiv:2509.09675 (2025)."},{"key":"e_1_3_2_1_8_1","unstructured":"DroidRun Team. 2025. DroidRun: A framework for controlling mobile devices through LLM agents. https:\/\/github.com\/droidrun\/droidrun MIT License API and CLI documented in README and docs."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00034"},{"key":"e_1_3_2_1_10_1","volume-title":"Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680","author":"Guo Taicheng","year":"2024","unstructured":"Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models. arXiv preprint arXiv:2511.05286","author":"Hao Teqi","year":"2025","unstructured":"Teqi Hao, Xioayu Tan, Shaojie Shi, Yinghui Xu, and Xihe Qiu. 2025. Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models. arXiv preprint arXiv:2511.05286 (2025)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639149"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108352"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3170427.3188532"},{"key":"e_1_3_2_1_15_1","unstructured":"JT-GUIAgent Team. 2025. JT-GUIAgent-V1: A Planner\u2013Grounder Agent for Reliable GUI Interaction. https:\/\/github.com\/JT-GUIAgent\/JT-GUIAgent Project description; no public paper available as of now."},{"key":"e_1_3_2_1_16_1","volume-title":"AndroidGen: Building an Android Language Agent under Data Scarcity. arXiv preprint arXiv:2504.19298","author":"Lai Hanyu","year":"2025","unstructured":"Hanyu Lai, Junjie Gao, Xiao Liu, Yifan Xu, Shudan Zhang, Yuxiao Dong, and Jie Tang. 2025. AndroidGen: Building an Android Language Agent under Data Scarcity. arXiv preprint arXiv:2504.19298 (2025)."},{"key":"e_1_3_2_1_17_1","volume-title":"WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making. arXiv preprint arXiv:2506.06725","author":"Levy Guillaume","year":"2025","unstructured":"Guillaume Levy, Cedric Colas, Pierre-Yves Oudeyer, Thomas Carta, and Clement Romac. 2025. WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making. arXiv preprint arXiv:2506.06725 (2025)."},{"key":"e_1_3_2_1_18_1","volume-title":"MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation. arXiv preprint arXiv:2507.16853","author":"Li Ning","year":"2025","unstructured":"Ning Li, Xiangmou Qu, Jiamu Zhou, Jun Wang, Muning Wen, Kounianhua Du, Xingyu Lou, Qiuying Peng, Jun Wang, and Weinan Zhang. 2025. MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation. arXiv preprint arXiv:2507.16853 (2025). https:\/\/arxiv.org\/abs\/2507.16853"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714768"},{"key":"e_1_3_2_1_20_1","volume-title":"Jiadai Sun, Jiaqi Wang, et al.","author":"Liu Xiao","year":"2024","unstructured":"Xiao Liu, Bo Qin, Dongzhu Liang, Guang Dong, Hanyu Lai, Hanchen Zhang, Hanlin Zhao, Iat Long Iong, Jiadai Sun, Jiaqi Wang, et al., 2024. Autoglm: Autonomous foundation agents for GUIs. arXiv preprint arXiv:2411.00820 (2024). https:\/\/arxiv.org\/abs\/2411.00820"},{"key":"e_1_3_2_1_21_1","unstructured":"LX-GUIAgent. 2025. LX-GUIAgent: An advanced GUI Agent developed by China Mobile's LingXi. https:\/\/github.com\/LX-GUIAgent\/LX-GUIAgent."},{"key":"e_1_3_2_1_22_1","volume-title":"The landscape of emerging ai agent architectures for reasoning, planning, and tool calling: A survey. arXiv preprint arXiv:2404.11584","author":"Masterman Tula","year":"2024","unstructured":"Tula Masterman, Sandi Besen, Mason Sawtell, and Alex Chao. 2024. The landscape of emerging ai agent architectures for reasoning, planning, and tool calling: A survey. arXiv preprint arXiv:2404.11584 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20743"},{"key":"e_1_3_2_1_24_1","unstructured":"Micro Focus. 2000. SilkTest: Functional and Regression Testing Tool. Accessed: 2025-09-18."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"e_1_3_2_1_26_1","volume-title":"Ui-tars: Pioneering automated gui interaction with native agents. arXiv preprint arXiv:2501.12326","author":"Qin Yujia","year":"2025","unstructured":"Yujia Qin, Yining Ye, Junjie Fang, Haoming Wang, Shihao Liang, Shizuo Tian, Junda Zhang, Jiahao Li, Yunxin Li, Shijue Huang, et al., 2025. Ui-tars: Pioneering automated gui interaction with native agents. arXiv preprint arXiv:2501.12326 (2025)."},{"key":"e_1_3_2_1_27_1","unstructured":"Christopher Rawles Sarah Clinckemaillie Yifan Chang Jonathan Waltz Gabrielle Lau Marybeth Fair Alice Li William Bishop Wei Li Folawiyo Campbell-Ajala Daniel Toyama Robert Berry Divya Tyamagundlu Timothy Lillicrap and Oriana Riva. 2024. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents. arXiv:2405.14573 [cs.AI]"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3115.003.0030"},{"key":"e_1_3_2_1_29_1","unstructured":"Fei Tang Haolei Xu Hang Zhang Siqi Chen Xingyu Wu Yongliang Shen Wenqi Zhang Guiyang Hou Zeqi Tan Yuchen Yan et al. 2025. A survey on (m) llm-based gui agents. arXiv preprint arXiv:2504.13865 (2025)."},{"key":"e_1_3_2_1_30_1","unstructured":"JT-GUIAgent Team. 2025. JT-GUIAgent: GUI Agent for Android Applications. https:\/\/github.com\/JT-GUIAgent\/JT-GUIAgent."},{"key":"e_1_3_2_1_31_1","volume-title":"GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent. In Annual Meeting of the Association for Computational Linguistics (ACL).","author":"Xie Bin","year":"2025","unstructured":"Bin Xie, Rui Shao, Gongwei Chen, Kaiwen Zhou, Yinchuan Li, Jie Liu, Min Zhang, and Liqiang Nie. 2025. GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent. In Annual Meeting of the Association for Computational Linguistics (ACL)."},{"key":"e_1_3_2_1_32_1","volume-title":"MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents. arXiv preprint arXiv:2509.18119","author":"Xu Yifan","year":"2025","unstructured":"Yifan Xu, Xiao Liu, Xinghan Liu, Jiaqi Fu, Hanchen Zhang, Bohao Jing, Shudan Zhang, Yuting Wang, Wenyi Zhao, and Yuxiao Dong. 2025. MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents. arXiv preprint arXiv:2509.18119 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"Aria-ui: Visual grounding for gui instructions. arXiv preprint arXiv:2412.16256","author":"Yang Yuhao","year":"2024","unstructured":"Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Chao Huang, and Junnan Li. 2024. Aria-ui: Visual grounding for gui instructions. arXiv preprint arXiv:2412.16256 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_35_1","unstructured":"Jiabo Ye Xi Zhang Haiyang Xu Haowei Liu Junyang Wang Zhaoqing Zhu Ziwei Zheng Feiyu Gao Junjie Cao Zhengxi Lu et al. 2025. Mobile-Agent-v3: Foundational Agents for GUI Automation. arXiv preprint arXiv:2508.15144 (2025). https:\/\/arxiv.org\/abs\/2508.15144"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Simon Zhai Hao Bai Zipeng Lin Jiayi Pan Peter Tong Yifei Zhou Alane Suhr Saining Xie Yann LeCun Yi Ma et al. 2024. Fine-tuning large vision-language models as decision-making agents via reinforcement learning. Advances in neural information processing systems Vol. 37 (2024) 110935-110971.","DOI":"10.52202\/079017-3522"},{"key":"e_1_3_2_1_37_1","volume-title":"Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps. arXiv preprint arXiv:2505.10593","author":"Zhao Shanhui","year":"2025","unstructured":"Shanhui Zhao, Hao Wen, Wenjie Du, Cheng Liang, Yunxin Liu, Xiaozhou Ye, Ye Ouyang, and Yuanchun Li. 2025. LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps. arXiv preprint arXiv:2505.10593 (2025)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:55:33Z","timestamp":1783151733000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":38,"alternative-id":["10.1145\/3774904.3792257","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792257","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}