{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:11:49Z","timestamp":1783786309684,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228553","type":"print"},{"value":"9789819228560","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-2856-0_34","type":"book-chapter","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:16:01Z","timestamp":1783782961000},"page":"476-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain Adaptation of\u00a0MLLM-Based GUI Agents in\u00a0Documentation-Rich Environments with\u00a0Standard Operating Procedures"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8807-7343","authenticated-orcid":false,"given":"Lingzhong","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9902-6653","authenticated-orcid":false,"given":"Ziqi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0945-8790","authenticated-orcid":false,"given":"Pengzhou","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5387-7821","authenticated-orcid":false,"given":"Zongru","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3737-5305","authenticated-orcid":false,"given":"Zheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5194-1570","authenticated-orcid":false,"given":"Gongshen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4183-3645","authenticated-orcid":false,"given":"Zhuosheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Bai, H., Zhou, Y., Cemri, M., Pan, J., Suhr, A.: Digirl: training in-the-wild device-control agents with autonomous reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 12461\u201312495 (2024)","DOI":"10.52202\/079017-0397"},{"key":"34_CR2","unstructured":"Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., et\u00a0al.: Qwen3-vl technical report. arXiv:2511.21631 (2025)"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, K., Sun, Q., Chu, Y., Xu, F., YanTao, L., et\u00a0al.: Seeclick: harnessing GUI grounding for advanced visual GUI agents. In: ACL, pp. 9313\u20139332 (2024)","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Fereidouni, M., Mosharrof, A., Siddique, A.: Grounded language agent for product search via intelligent web interactions. In: CustomNLP4U, pp. 63\u201375. (2024)","DOI":"10.18653\/v1\/2024.customnlp4u-1.7"},{"key":"34_CR5","unstructured":"Gao, X., Hu, C., Chen, B., Li, T.: Chain-of-memory: enhancing GUI agents for cross-application navigation (2025). arXiv:2506.18158"},{"key":"34_CR6","unstructured":"Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., et\u00a0al.: Retrieval-augmented generation for large language models: a survey. arXiv:2312.10997 (2023)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Guan, Z., Li, J.C.L., Hou, Z., Zhang, P., Xu, D.: Kg-rag: enhancing GUI agent decision-making via knowledge graph-driven retrieval-augmented generation. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 5396\u20135405 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.274"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"G\u00fcnther, M., Sturua, S., Akram, M.K., Mohr, I.: jina-embeddings-v4: universal embeddings for multimodal multilingual retrieval. In: Proceedings of the 5th Workshop on Multilingual Representation Learning, pp. 531\u2013550 (2025)","DOI":"10.18653\/v1\/2025.mrl-main.36"},{"key":"34_CR9","unstructured":"Guo, D., Wu, F., Zhu, F., Leng, F., Shi, G.: Seed1.5-vl technical report (2025). arXiv:2505.07062"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, W., Heng, Y.W., Chen, T.H.P., Wang, Y.: Agent-sama: state-aware mobile assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 29459\u201329467 (2026)","DOI":"10.1609\/aaai.v40i35.40187"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, W., Lv, Q., Xu, J., Yu, W.: Cogagent: a visual language model for gui agents. In: CVPR, pp. 14281\u201314290 (2024)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"34_CR12","unstructured":"Hu, S., Ouyang, M., Gao, D., Shou, M.Z.: The dawn of GUI agent: a preliminary case study with claude 3.5 computer use. arXiv:2411.10323 (2024)"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Hu, X., Xiong, T., Yi, B., Wei, Z., Xiao, R.: OS agents: a survey on MLLM-based agents for general computing devices use. arXiv:2508.04482 (2025)","DOI":"10.20944\/preprints202412.2294.v1"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Lee, S., Yoon, S., Lee, S., et\u00a0al.: Log2plan: an adaptive GUI automation framework integrated with task mining approach. In: Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology, pp. 1\u201313 (2025)","DOI":"10.1145\/3746059.3747663"},{"key":"34_CR15","unstructured":"Liu, A., Mei, A., Lin, B., Xue, B., Wang, B.: Deepseek-v3.2: pushing the frontier of open large language models. arXiv:2508.04482 (2025)"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Liu, B., Jianxiang, Z., Meng, D., Lu, H.: An evaluation mechanism of LLM-based agents on manipulating APIS. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 4649\u20134662 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.267"},{"key":"34_CR17","unstructured":"Liu, X., Qin, B., Liang, D., Dong, G., Lai, H.: Autoglm: autonomous foundation agents for guis. arXiv:2411.00820 (2024)"},{"key":"34_CR18","unstructured":"Loo, G., Liu, C., Yin, Q., Chen, X., Chen, J., et\u00a0al.: Mobilerag: enhancing mobile agent with retrieval-augmented generation. arXiv:2509.03891 (2025)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Louvan, S., Magnini, B.: Recent neural methods on slot filling and intent classification for task-oriented dialogue systems: a survey. In: COLING, pp. 480\u2013496 (2020)","DOI":"10.18653\/v1\/2020.coling-main.42"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Nguyen, D., Chen, J., Wang, Y., Wu, G.: GUI agents: a survey. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 22522\u201322538 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.1158"},{"key":"34_CR21","unstructured":"Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., et\u00a0al.: Toolllm: facilitating large language models to master 16000+ real-world apis. arXiv:2307.16789 (2023)"},{"key":"34_CR22","unstructured":"Qin, Y., Ye, Y., Fang, J., Wang, H., Liang, S.: Ui-tars: pioneering automated GUI interaction with native agents. arXiv:2501.12326 (2025)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Rawles, C., Li, A., Rodriguez, D., Riva, O., Lillicrap, T.: Androidinthewild: a large-scale dataset for android device control. In: Advances in Neural Information Processing Systems, pp. 59708\u201359728 (2023)","DOI":"10.52202\/075280-2609"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Wang, J., Xu, H., Jia, H., Zhang, X., Yan, M.: Mobile-agent-v2: mobile device operation assistant with effective navigation via multi-agent collaboration. In: Advances in Neural Information Processing Systems, pp. 2686\u20132710 (2024)","DOI":"10.52202\/079017-0088"},{"key":"34_CR25","unstructured":"Wang, S., Liu, W., Chen, J., Zhou, Y., Gan, W.: GUI agents with foundation models: a comprehensive survey (2024). arXiv:2411.04890"},{"key":"34_CR26","unstructured":"Wang, T., Wu, Z., Liu, J., Hao, J., Wang, J., Shao, K.: Distrl: an asynchronous distributed reinforcement learning framework for on-device control agents. arXiv:2410.14803 (2024)"},{"key":"34_CR27","unstructured":"Wang, X., Liu, B.: Oscar: operating system control via state-aware reasoning and re-planning. arXiv:2410.18963 (2024)"},{"key":"34_CR28","unstructured":"Wang, Z., Xu, H., Wang, J., Zhang, X., Yan, M., et\u00a0al.: Mobile-agent-e: self-evolving mobile assistant for complex tasks. arXiv:2501.11733 (2025)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Wen, H., Li, Y., Liu, G., Zhao, S., Yu, T., et\u00a0al.: Autodroid: LLM-powered task automation in android. In: Proceedings of the 30th annual international conference on Mobile computing and networking, pp. 543\u2013557 (2024)","DOI":"10.1145\/3636534.3649379"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Wu, J., Harris, I., Zhao, H.: Spoken language understanding for task-oriented dialogue systems with augmented memory networks. In: NAACL, pp. 797\u2013806 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.63"},{"key":"34_CR31","unstructured":"Wu, Z., Wu, Z., Xu, F., Wang, Y., Sun, Q., et\u00a0al.: OS-atlas: a foundation action model for generalist GUI agents. arXiv:2410.23218 (2024)"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., Jimenez, C.E., Wettig, A., Lieret, K., Yao, S.: Swe-agent: agent-computer interfaces enable automated software engineering. In: Advances in Neural Information Processing Systems, pp. 50528\u201350652 (2024)","DOI":"10.52202\/079017-1601"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Yao, S., Chen, H., Yang, J., Narasimhan, K.: Webshop: towards scalable real-world web interaction with grounded language agents. In: Advances in Neural Information Processing Systems, pp. 20744\u201320757 (2022)","DOI":"10.52202\/068431-1508"},{"key":"34_CR34","unstructured":"Ye, J., Zhang, X., Xu, H., Liu, H., Wang, J.: Mobile-agent-v3: fundamental agents for GUI automation. arXiv:2508.15144 (2025)"},{"key":"34_CR35","unstructured":"Zhang, C., He, S., Qian, J., Li, B., Li, L., et\u00a0al.: Large language model-brained GUI agents: a survey. arXiv:2411.18279 (2024)"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, C., Yang, Z., Liu, J., Li, Y., Han, Y.: Appagent: multimodal agents as smartphone users. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pp. 1\u201320 (2025)","DOI":"10.1145\/3706598.3713600"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Z., Chen, K., Ma, X., Yang, M., et\u00a0al.: Dynamic planning for LLM-based graphical user interface automation. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 1304\u20131320 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.70"},{"key":"34_CR38","unstructured":"Zhang, X., Wang, H.: A joint model of intent determination and slot filling for spoken language understanding. In: IJCAI, pp, 2993\u20132999 (2016)"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, A.: You only look at screens: multimodal chain-of-action agents. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 3132\u20133149 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.186"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Li, J., Zhang, Y., Lu, H., Li, G.: Mobile-agent-rag: driving smart multi-agent coordination with contextual knowledge empowerment for long-horizon mobile automation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 29939\u201329947 (2026)","DOI":"10.1609\/aaai.v40i35.40241"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2856-0_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:16:06Z","timestamp":1783782966000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2856-0_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"ISBN":["9789819228553","9789819228560"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2856-0_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]},"assertion":[{"value":"12 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}