{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:59Z","timestamp":1765343159794,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372408, 62476245"],"award-info":[{"award-number":["62372408, 62476245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755189","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"6878-6887","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PG-Agent: An Agent Powered by Page Graph"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1953-1156","authenticated-orcid":false,"given":"Weizhi","family":"Chen","sequence":"first","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4479-3738","authenticated-orcid":false,"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5553-8037","authenticated-orcid":false,"given":"Leyang","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-1041","authenticated-orcid":false,"given":"Sheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1765-9924","authenticated-orcid":false,"given":"Xiaoxuan","family":"Tang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1097-2044","authenticated-orcid":false,"given":"Jiajun","family":"Bu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1664-6425","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6605-9793","authenticated-orcid":false,"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"unstructured":"Meta AI. 2024. Llama 3. https:\/\/github.com\/meta-llama\/llama3 Accessed: 2024-11-12.","key":"e_1_3_2_1_1_1"},{"unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025).","key":"e_1_3_2_1_2_1"},{"doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2024d. BGE M3-Embedding: Multi-Lingual Multi-Functionality Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. arXiv:2402.03216 [cs.CL]","key":"e_1_3_2_1_3_1","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"doi-asserted-by":"crossref","unstructured":"Minghao Chen Yihang Li Yanting Yang Shiyu Yu Binbin Lin and Xiaofei He. 2024a. AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning. arXiv:2405.16247 [cs.AI] https:\/\/arxiv.org\/abs\/2405.16247","key":"e_1_3_2_1_4_1","DOI":"10.52202\/079017-0019"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.18653\/v1\/2024.emnlp-main.845"},{"doi-asserted-by":"crossref","unstructured":"Zhe Chen Weiyun Wang Hao Tian Shenglong Ye Zhangwei Gao Erfei Cui Wenwen Tong Kongzhi Hu Jiapeng Luo Zheng Ma et al. 2024c. How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821 (2024).","key":"e_1_3_2_1_6_1","DOI":"10.1007\/s11432-024-4231-5"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Deng Xiang","year":"2023","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samual Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. Mind2Web: Towards a Generalist Agent for the Web. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023."},{"doi-asserted-by":"crossref","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arXiv:2401.08281 [cs.LG]","key":"e_1_3_2_1_9_1","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"e_1_3_2_1_10_1","volume-title":"Robert Osazuwa Ness, and Jonathan Larson","author":"Edge Darren","year":"2025","unstructured":"Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv:2404.16130 [cs.CL] https:\/\/arxiv.org\/abs\/2404.16130"},{"unstructured":"Yao Fu Dong-Ki Kim Jaekyeom Kim Sungryull Sohn Lajanugen Logeswaran Kyunghoon Bae and Honglak Lee. 2024. AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents. arXiv:2403.08978 [cs.CL] https:\/\/arxiv.org\/abs\/2403.08978","key":"e_1_3_2_1_11_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_2_1_13_1","volume-title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory. arXiv:2212.05221 [cs.CV] https:\/\/arxiv.org\/abs\/2212.05221","author":"Hu Ziniu","year":"2023","unstructured":"Ziniu Hu, Ahmet Iscen, Chen Sun, Zirui Wang, Kai-Wei Chang, Yizhou Sun, Cordelia Schmid, David A. Ross, and Alireza Fathi. 2023. REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory. arXiv:2212.05221 [cs.CV] https:\/\/arxiv.org\/abs\/2212.05221"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1145\/3637528.3671620"},{"key":"e_1_3_2_1_15_1","volume-title":"Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela.","author":"Lewis Patrick","year":"2021","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv:2005.11401 [cs.CL] https:\/\/arxiv.org\/abs\/2005.11401"},{"unstructured":"Yanda Li Chi Zhang Wanqi Yang Bin Fu Pei Cheng Xin Chen Ling Chen and Yunchao Wei. 2024b. AppAgent v2: Advanced Agent for Flexible Mobile Interactions. arXiv:2408.11824 [cs.HC] https:\/\/arxiv.org\/abs\/2408.11824","key":"e_1_3_2_1_16_1"},{"unstructured":"Zijian Li Qingyan Guo Jiawei Shao Lei Song Jiang Bian Jun Zhang and Rui Wang. 2024a. Graph Neural Network Enhanced Retrieval for Question Answering of LLMs. arXiv:2406.06572 [cs.CL] https:\/\/arxiv.org\/abs\/2406.06572","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","volume-title":"Showui: One vision-language-action model for gui visual agent. arXiv preprint arXiv:2411.17465","author":"Lin Kevin Qinghong","year":"2024","unstructured":"Kevin Qinghong Lin, Linjie Li, Difei Gao, Zhengyuan Yang, Shiwei Wu, Zechen Bai, Weixian Lei, Lijuan Wang, and Mike Zheng Shou. 2024. Showui: One vision-language-action model for gui visual agent. arXiv preprint arXiv:2411.17465 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/ICSME.2017.27"},{"unstructured":"Nelson F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2023. Lost in the Middle: How Language Models Use Long Contexts. arXiv:2307.03172 [cs.CL] https:\/\/arxiv.org\/abs\/2307.03172","key":"e_1_3_2_1_20_1"},{"unstructured":"Xinwei Long Jiali Zeng Fandong Meng Zhiyuan Ma Kaiyan Zhang Bowen Zhou and Jie Zhou. 2024. Generative Multi-Modal Knowledge Retrieval with Large Language Models. arXiv:2401.08206 [cs.IR] https:\/\/arxiv.org\/abs\/2401.08206","key":"e_1_3_2_1_21_1"},{"unstructured":"Quanfeng Lu Wenqi Shao Zitao Liu Fanqing Meng Boxuan Li Botong Chen Siyuan Huang Kaipeng Zhang Yu Qiao and Ping Luo. 2024a. GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices. arXiv:2406.08451 [cs.CV] https:\/\/arxiv.org\/abs\/2406.08451","key":"e_1_3_2_1_22_1"},{"unstructured":"Yadong Lu Jianwei Yang Yelong Shen and Ahmed Awadallah. 2024b. OmniParser for Pure Vision Based GUI Agent. arXiv:2408.00203 [cs.CV] https:\/\/arxiv.org\/abs\/2408.00203","key":"e_1_3_2_1_23_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.18653\/v1\/2024.naacl-industry.41"},{"unstructured":"Dehai Min Nan Hu Rihui Jin Nuo Lin Jiaoyan Chen Yongrui Chen Yu Li Guilin Qi Yun Li Nijun Li and Qianren Wang. 2024b. Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data. arXiv:2402.12869 [cs.CL] https:\/\/arxiv.org\/abs\/2402.12869","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","volume-title":"ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science. arXiv:2311.12289 [cs.CL] https:\/\/arxiv.org\/abs\/2311.12289","author":"Munikoti Sai","year":"2023","unstructured":"Sai Munikoti, Anurag Acharya, Sridevi Wagle, and Sameera Horawalavithana. 2023. ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science. arXiv:2311.12289 [cs.CL] https:\/\/arxiv.org\/abs\/2311.12289"},{"doi-asserted-by":"crossref","unstructured":"Dang Nguyen Jian Chen Yu Wang Gang Wu Namyong Park Zhengmian Hu Hanjia Lyu Junda Wu Ryan Aponte Yu Xia Xintong Li Jing Shi Hongjie Chen Viet Dac Lai Zhouhang Xie Sungchul Kim Ruiyi Zhang Tong Yu Mehrab Tanjim Nesreen K. Ahmed Puneet Mathur Seunghyun Yoon Lina Yao Branislav Kveton Thien Huu Nguyen Trung Bui Tianyi Zhou Ryan A. Rossi and Franck Dernoncourt. 2024. GUI Agents: A Survey. arXiv:2412.13501 [cs.AI] https:\/\/arxiv.org\/abs\/2412.13501","key":"e_1_3_2_1_27_1","DOI":"10.18653\/v1\/2025.findings-acl.1158"},{"doi-asserted-by":"publisher","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. (1 2023). doi:10.26181\/25479208.v1","key":"e_1_3_2_1_28_1","DOI":"10.26181\/25479208.v1"},{"unstructured":"OpenAI. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774","key":"e_1_3_2_1_29_1"},{"doi-asserted-by":"crossref","unstructured":"Boci Peng Yun Zhu Yongchao Liu Xiaohe Bo Haizhou Shi Chuntao Hong Yan Zhang and Siliang Tang. 2024. Graph Retrieval-Augmented Generation: A Survey. arXiv:2408.08921 [cs.AI] https:\/\/arxiv.org\/abs\/2408.08921","key":"e_1_3_2_1_30_1","DOI":"10.1145\/3777378"},{"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_31_1"},{"key":"e_1_3_2_1_32_1","volume-title":"Lillicrap","author":"Rawles Christopher","year":"2023","unstructured":"Christopher Rawles, Alice Li, Daniel Rodriguez, Oriana Riva, and Timothy P. Lillicrap. 2023. Android in the Wild: A Large-Scale Dataset for Android Device Control. CoRR, Vol. abs\/2307.10088 (2023). showeprint2307.10088"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.18653\/v1\/2024.acl-long.397"},{"key":"e_1_3_2_1_34_1","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume":"36","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 8634-8652.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","first-page":"2686","article-title":"Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration","volume":"37","author":"Wang Junyang","year":"2025","unstructured":"Junyang Wang, Haiyang Xu, Haitao Jia, Xi Zhang, Ming Yan, Weizhou Shen, Ji Zhang, Fei Huang, and Jitao Sang. 2025a. Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration. Advances in Neural Information Processing Systems, Vol. 37 (2025), 2686-2710.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1007\/s11704-024-40231-1"},{"unstructured":"Yu Wang Nedim Lipka Ryan A. Rossi Alexa Siu Ruiyi Zhang and Tyler Derr. 2023. Knowledge Graph Prompting for Multi-Document Question Answering. arXiv:2308.11730 [cs.CL] https:\/\/arxiv.org\/abs\/2308.11730","key":"e_1_3_2_1_37_1"},{"unstructured":"Zhenhailong Wang Haiyang Xu Junyang Wang Xi Zhang Ming Yan Ji Zhang Fei Huang and Heng Ji. 2025b. Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks. arXiv:2501.11733 [cs.CL] https:\/\/arxiv.org\/abs\/2501.11733","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","volume-title":"Os-copilot: Towards generalist computer agents with self-improvement. arXiv preprint arXiv:2402.07456","author":"Wu Zhiyong","year":"2024","unstructured":"Zhiyong Wu, Chengcheng Han, Zichen Ding, Zhenmin Weng, Zhoumianze Liu, Shunyu Yao, Tao Yu, and Lingpeng Kong. 2024. Os-copilot: Towards generalist computer agents with self-improvement. arXiv preprint arXiv:2402.07456 (2024)."},{"unstructured":"Jianwei Yang Hao Zhang Feng Li Xueyan Zou Chunyuan Li and Jianfeng Gao. 2023. Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V. arXiv:2310.11441 [cs.CV] https:\/\/arxiv.org\/abs\/2310.11441","key":"e_1_3_2_1_40_1"},{"key":"e_1_3_2_1_41_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)."},{"unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu Tianchi Cai Haoyu Li Weilin Zhao Zhihui He et al. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint arXiv:2408.01800 (2024).","key":"e_1_3_2_1_42_1"},{"unstructured":"Antonio Jimeno Yepes Yao You Jan Milczek Sebastian Laverde and Renyu Li. 2024. Financial Report Chunking for Effective Retrieval Augmented Generation. arXiv:2402.05131 [cs.CL] https:\/\/arxiv.org\/abs\/2402.05131","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","volume-title":"Appagent: Multimodal agents as smartphone users. arXiv preprint arXiv:2312.13771","author":"Zhang Chi","year":"2023","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 preprint arXiv:2312.13771 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1609\/aaai.v38i17.29936"},{"unstructured":"Siyun Zhao Yuqing Yang Zilong Wang Zhiyuan He Luna K. Qiu and Lili Qiu. 2024b. Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely. arXiv:2409.14924 [cs.CL] https:\/\/arxiv.org\/abs\/2409.14924","key":"e_1_3_2_1_46_1"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:02:44Z","timestamp":1765342964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755189"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"alternative-id":["10.1145\/3746027.3755189","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755189","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}