{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:51:59Z","timestamp":1782478319502,"version":"3.54.5"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032297433","type":"print"},{"value":"9783032297440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"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\/978-3-032-29744-0_39","type":"book-chapter","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:43:22Z","timestamp":1782477802000},"page":"586-600","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Single-Agent vs. Multi-agents for\u00a0Automated Video Analysis of On-Screen Collaborative Learning Behaviors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0475-0541","authenticated-orcid":false,"given":"Likai","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5572-276X","authenticated-orcid":false,"given":"Shihui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"issue":"7","key":"39_CR1","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.3390\/math12071036","volume":"12","author":"MD Alahmadi","year":"2024","unstructured":"Alahmadi, M.D., Alshangiti, M.: Optimizing ocr performance for programming videos: the role of image super-resolution and large language models. Mathematics 12(7), 1036 (2024)","journal-title":"Mathematics"},{"key":"39_CR2","unstructured":"Anthropic: Claude 3.7 Sonnet and Claude Code (2025). https:\/\/www.anthropic.com\/news\/claude-3-7-sonnet, Accessed 23 September 2025"},{"key":"39_CR3","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"39_CR4","doi-asserted-by":"publisher","unstructured":"Bosetti, M., Zhang, S., Liberatori, B., Zara, G., Ricci, E., Rota, P.: Text-enhanced zero-shot action recognition: a training-free approach. In: International Conference on Pattern Recognition, pp. 327\u2013342. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-78354-8_21","DOI":"10.1007\/978-3-031-78354-8_21"},{"key":"39_CR5","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-030-20969-8_6","volume-title":"Visuospatial Processing for Education in Health and Natural Sciences","author":"JC Castro-Alonso","year":"2019","unstructured":"Castro-Alonso, J.C., Fiorella, L.: Interactive science multimedia and visuospatial processing. In: Castro-Alonso, J.C. (ed.) Visuospatial Processing for Education in Health and Natural Sciences, pp. 145\u2013173. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20969-8_6"},{"key":"39_CR6","unstructured":"Cesa-Bianchi, N., Gentile, C., Tironi, A., Zaniboni, L.: Incremental algorithms for hierarchical classification. Adv. Neural. Inf. Process. Syst. 17 (2004)"},{"key":"39_CR7","doi-asserted-by":"publisher","unstructured":"Chen, X., Lin, Y., Zhang, Y., Huang, W.: Autoeval-video: an automatic benchmark for assessing large vision language models in open-ended video question answering. In: European Conference on Computer Vision, pp. 179\u2013195. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-73113-6_11","DOI":"10.1007\/978-3-031-73113-6_11"},{"key":"39_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jslw.2022.100931","volume":"58","author":"A Cheung","year":"2022","unstructured":"Cheung, A.: Verbal and on-screen peer interactions of efl learners during multimodal collaborative writing: a multiple case-study. J. Second. Lang. Writ. 58, 100931 (2022)","journal-title":"J. Second. Lang. Writ."},{"issue":"4","key":"39_CR9","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1080\/00461520.2014.965823","volume":"49","author":"MT Chi","year":"2014","unstructured":"Chi, M.T., Wylie, R.: The icap framework: linking cognitive engagement to active learning outcomes. Educ. Psychol. 49(4), 219\u2013243 (2014)","journal-title":"Educ. Psychol."},{"issue":"4","key":"39_CR10","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/s11412-008-9052-6","volume":"3","author":"G Erkens","year":"2008","unstructured":"Erkens, G., Janssen, J.: Automatic coding of dialogue acts in collaboration protocols. Int. J. Comput.-Support. Collab. Learn. 3(4), 447\u2013470 (2008)","journal-title":"Int. J. Comput.-Support. Collab. Learn."},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Falco, M., Robiolo, G.: Tendencies in multi-agents systems: A systematic literature review (2020)","DOI":"10.19153\/cleiej.23.1.1"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Feng, S., Yan, L., Zhao, L., Maldonado, R.M., Ga\u0161evi\u0107, D.: Heterogenous network analytics of small group teamwork: Using multimodal data to uncover individual behavioral engagement strategies. In: Proceedings of the 14th Learning Analytics and Knowledge Conference, pp. 587\u2013597. (2024)","DOI":"10.1145\/3636555.3636918"},{"issue":"1","key":"39_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617362","volume":"31","author":"J Gao","year":"2023","unstructured":"Gao, J., Choo, K.T.W., Cao, J., Lee, R.K.W., Perrault, S.: Coaicoder: examining the effectiveness of ai-assisted human-to-human collaboration in qualitative analysis. ACM Trans. Comput.-Human Interact. 31(1), 1\u201338 (2023)","journal-title":"ACM Trans. Comput.-Human Interact."},{"key":"39_CR14","unstructured":"Gao, Z., et al.: Multi-modal agent tuning: Building a vlm-driven agent for efficient tool usage (2025). https:\/\/arxiv.org\/abs\/2412.15606"},{"issue":"1","key":"39_CR15","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s40594-023-00407-w","volume":"10","author":"S Gomes","year":"2023","unstructured":"Gomes, S., Costa, L., Martinho, C., Dias, J., Xex\u00e9o, G., Moura Santos, A.: Modeling students\u2019 behavioral engagement through different in-class behavior styles. Inter. J. STEM Educ. 10(1), 21 (2023)","journal-title":"Inter. J. STEM Educ."},{"key":"39_CR16","unstructured":"Jiang, Y.H., et al.: Ai agent for education: von neumann multi-agent system framework (2024). https:\/\/arxiv.org\/abs\/2501.00083"},{"issue":"5","key":"39_CR17","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1177\/07356331221136888","volume":"61","author":"HY Lee","year":"2023","unstructured":"Lee, H.Y., Cheng, Y.P., Wang, W.S., Lin, C.J., Huang, Y.M.: Exploring the learning process and effectiveness of stem education via learning behavior analysis and the interactive-constructive-active-passive framework. J. Educ. Comput. Res. 61(5), 951\u2013976 (2023)","journal-title":"J. Educ. Comput. Res."},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., Yan, L., Zhao, L., Martinez-Maldonado, R., Gasevic, D.: Cvpe: a computer vision approach for scalable and privacy-preserving socio-spatial, multimodal learning analytics. In: LAK23: 13th International Learning Analytics and Knowledge Conference, pp. 175\u2013185. (2023)","DOI":"10.1145\/3576050.3576145"},{"key":"39_CR19","unstructured":"Liu, R., Liu, Z., Tang, J., Ma, Y., Pi, R., Zhang, J., Chen, Q.: Longvideoagent: multi-agent reasoning with long videos. arXiv preprint arXiv:2512.20618 (2025)"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Oh, J., Sundar, S.S.: What happens when you click and drag: unpacking the relationship between on-screen interaction and user engagement with an anti-smoking website. Health communication (2020)","DOI":"10.1080\/10410236.2018.1560578"},{"key":"39_CR21","unstructured":"OpenAI: Introducing GPT-4.1 in the API (2025). https:\/\/openai.com\/index\/gpt-4-1\/, Accessed: 23 September 2025"},{"key":"39_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2024.105163","volume":"223","author":"R Schiller","year":"2024","unstructured":"Schiller, R., Fleckenstein, J., Mertens, U., Horbach, A., Meyer, J.: Understanding the effectiveness of automated feedback: using process data to uncover the role of behavioral engagement. Comput. Educ. 223, 105163 (2024)","journal-title":"Comput. Educ."},{"issue":"5","key":"39_CR23","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1111\/bjet.12993","volume":"51","author":"K Sharma","year":"2020","unstructured":"Sharma, K., Giannakos, M.: Multimodal data capabilities for learning: what can multimodal data tell us about learning? Br. J. Edu. Technol. 51(5), 1450\u20131484 (2020)","journal-title":"Br. J. Edu. Technol."},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Shriram, S., et al.: Towards a multi-agent vision-language system for zero-shot novel hazardous object detection for autonomous driving safety (2025). arxiv preprint arXiv:2504.13399","DOI":"10.1109\/CASE58245.2025.11163861"},{"issue":"2","key":"39_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1080\/07370024.2013.789347","volume":"29","author":"SS Sundar","year":"2014","unstructured":"Sundar, S.S., Bellur, S., Oh, J., Xu, Q., Jia, H.: User experience of on-screen interaction techniques: an experimental investigation of clicking, sliding, zooming, hovering, dragging, and flipping. Human-Comput. Interact. 29(2), 109\u2013152 (2014)","journal-title":"Human-Comput. Interact."},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Teotia, J., Zhang, X., Mao, R., Cambria, E.: Evaluating vision language models in detecting learning engagement. In: 2024 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 496\u2013502. IEEE (2024)","DOI":"10.1109\/ICDMW65004.2024.00069"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Van Rijsbergen, C.J.: The geometry of information retrieval, Cambridge University Press (2004)","DOI":"10.1017\/CBO9780511543333"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Grounded-videollm: sharpening fine-grained temporal grounding in video large language models. arXiv preprint arXiv:2410.03290 (2024)","DOI":"10.18653\/v1\/2025.findings-emnlp.50"},{"issue":"6","key":"39_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang, L., et al.: A survey on large language model based autonomous agents. Front. Comp. Sci. 18(6), 186345 (2024)","journal-title":"Front. Comp. Sci."},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Embodied multi-modal agent trained by an llm from a parallel textworld. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26275\u201326285 (June 2024)","DOI":"10.1109\/CVPR52733.2024.02482"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liu, X.: A re-examination of text categorization methods. In: Proceedings of the 22nd annual international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 42\u201349. (1999)","DOI":"10.1145\/312624.312647"},{"key":"39_CR32","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Yu, C., et al.: A survey on agent workflow-status and future. In: 2025 8th International Conference on Artificial Intelligence and Big Data (ICAIBD), pp. 770\u2013781. IEEE (2025)","DOI":"10.1109\/ICAIBD64986.2025.11082076"},{"issue":"8","key":"39_CR34","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29744-0_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:43:47Z","timestamp":1782477827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29744-0_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,27]]},"ISBN":["9783032297433","9783032297440"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29744-0_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,27]]},"assertion":[{"value":"27 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seoul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"29 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.aied-conference.org\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}