{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:14:52Z","timestamp":1783602892452,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533428","type":"print"},{"value":"9789819533435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3343-5_29","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T06:29:47Z","timestamp":1763792987000},"page":"375-387","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ReGA: Reasoning and\u00a0Grounding Decoupled GUI Navigation Agents"],"prefix":"10.1007","author":[{"given":"Feiyue","family":"Ni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanchu","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyi","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjie","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"29_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"29_CR2","unstructured":"Anil, R., et\u00a0al.: Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"29_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"29_CR4","unstructured":"Bavishi, R., et al.: Introducing our multimodal models (2023). https:\/\/www.adept.ai\/blog\/fuyu-8b"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Deng, X., et al.: Mind2web: towards a generalist agent for the web. In: NeurIPS (2023)","DOI":"10.52202\/075280-1220"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1), pp. 4171\u20134186. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"29_CR7","unstructured":"Furuta, H., et al.: Multimodal web navigation with instruction-finetuned foundation models. arXiv preprint arXiv:2305.11854 (2023)"},{"key":"29_CR8","unstructured":"Guan, Y., et al.: Intelligent virtual assistants with LLM-based process automation. arXiv preprint arXiv:2312.06677 (2023)"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Hong, W., et al.: Cogagent: a visual language model for GUI agents. In: CVPR, pp. 14281\u201314290. IEEE (2024)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"29_CR10","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Kim, G., Baldi, P., McAleer, S.: Language models can solve computer tasks. In: NeurIPS (2023)","DOI":"10.52202\/075280-1723"},{"key":"29_CR12","unstructured":"Li, B., Zhang, P., Yang, J., Zhang, Y., Pu, F., Liu, Z.: Otterhd: a high-resolution multi-modality model. arXiv preprint arXiv:2311.04219 (2023)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Li, C., et\u00a0al.: mplug: effective and efficient vision-language learning by cross-modal skip-connections. arXiv preprint arXiv:2205.12005 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"29_CR14","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of Machine Learning Research, ICML, vol.\u00a0202, pp. 19730\u201319742. PMLR (2023)"},{"key":"29_CR15","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., Zhang, M.: Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhang, Z., Zhao, H.: Comprehensive cognitive LLM agent for smartphone GUI automation. arXiv preprint arXiv:2402.11941 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.539"},{"key":"29_CR19","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"29_CR20","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of Machine Learning Research, ICML, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"29_CR21","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Rawles, C., Li, A., Rodriguez, D., Riva, O., Lillicrap, T.P.: Androidinthewild: a large-scale dataset for android device control. In: NeurIPS (2023)","DOI":"10.52202\/075280-2609"},{"key":"29_CR23","unstructured":"Shi, T., Karpathy, A., Fan, L., Hernandez, J., Liang, P.: World of bits: an open-domain platform for web-based agents. In: Proceedings of the International Conference on Machine Learning, pp. 3135\u20133144. PMLR (2017)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Sun, L., Chen, X., Chen, L., Dai, T., Zhu, Z., Yu, K.: META-GUI: towards multi-modal conversational agents on mobile GUI. In: EMNLP, pp. 6699\u20136712. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.449"},{"key":"29_CR25","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"29_CR26","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm:pre-training of text and layout for document image understanding. In: KDD, pp. 1192\u20131200. ACM (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"29_CR29","unstructured":"Yan, A., et\u00a0al.: GPT-4v in wonderland: large multimodal models for zero-shot smartphone GUI navigation. arXiv preprint arXiv:2311.07562 (2023)"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Zhan, Z., Zhang, A.: You only look at screens: multimodal chain-of-action agents. arXiv preprint arXiv:2309.11436 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.186"},{"key":"29_CR31","unstructured":"Zheng, B., Gou, B., Kil, J., Sun, H., Su, Y.: GPT-4v(ision) is a generalist web agent, if grounded. In: ICML. OpenReview.net (2024)"},{"key":"29_CR32","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3343-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T12:28:28Z","timestamp":1783600108000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3343-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533428","9789819533435"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3343-5_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}