koz"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"Bulletin of Manash Kozybayev North Kazakhstan University2958-003X2958-0048М. Қозыбаев атындағы СҚУ10.54596/2958-0048-2025-4-182-194koz-2320Research ArticleИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИINFORMATION AND COMMUNICATION TECHNOLOGIESИнтеллектуальные агенты в образовательных технологияхIntelligent agents in educational technologieshttps://orcid.org/0000-0002-0074-2966АстапенкоН. В.AstapenkoN. V.

Астапенко Наталья Владимировна - доцент, "Информационно-коммуникационные технологии".

Петропавловск

Corresponding author, Associate Professor of the Information and Communication Technologies, PhD, Kozybayev University.

Petrolpavlovsk

astankin@mail.ruНАО «Северо-Казахстанский университет имени Манаша Козыбаева»КазахстанManash Kozybayev North Kazakhstan University NPLCKazakhstan20251201202604 (68)182194Copyright © Астапенко Н.В., 20252025Астапенко Н.В.Astapenko N.V.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.ku.edu.kz/jour/article/view/2320

Искусственный интеллект (ИИ) ускоренно трансформирует образование, переводя его от статичных курсов к персонализированным и адаптивным экосистемам. По данным международных организаций (в т.ч. UNESCO), ИИ становится инфраструктурным элементом высшей школы; в этой рамке интеллектуальные агенты (ИА) выступают механизмом интеграции педагогических целей, данных об обучающихся и стратегий адаптации в реальном времени. Цель статьи — систематизировать архитектурные и функциональные принципы использования ИА в образовательных технологиях и проанализировать практики внедрения в контексте современного направления AIEd. Рассматривается эволюция от монолитных интеллектуальных обучающих систем (ИОС) к распределённым многоагентным системам (МАС) и диалоговым агентам на базе больших языковых моделей (БЯМ/LLM). Обобщаются эмпирические результаты по эффективности классических ИОС и сопоставляются с новыми практиками LLM-агентов на массовых платформах. Научная новизна состоит в аналитическом сопоставлении трёх уровней: архитектурного (ИОС/МАС), инструментального (диалоговые и аналитические функции) и институционального (политики, метрики внедрения) на материале 2023–2025 гг. Дополнительно формулируются методические ориентиры ответственного внедрения (объяснимость, справедливость, защита данных), обеспечивающие баланс между автоматизацией и педагогическим контролем и задающие требования к масштабируемым, этичным и прозрачным экосистемам обучения.

Artificial intelligence (AI) is rapidly transforming education, shifting it from static courses to personalized, adaptive learning ecosystems. According to international organizations (including UNESCO), AI is becoming an infrastructural element of higher education; within this frame, intelligent agents (IAs) serve as a mechanism for integrating pedagogical objectives, learner data, and real-time adaptation strategies. This article aims to systematize the architectural and functional principles of using intelligent agents in educational technologies and to analyze implementation practices within contemporary AIEd. We trace the evolution from monolithic Intelligent Tutoring Systems (ITS) to distributed Multi-Agent Systems (MAS) and dialog agents powered by Large Language Models (LLMs). Empirical findings on the effectiveness of classical ITS are synthesized and compared with emerging practices of LLM-based agents on mass-scale platforms. The study’s novelty lies in an analytical comparison across three levels—architectural (ITS/MAS), instrumental (dialogic and analytic functions), and institutional (policies and deployment metrics)—grounded in evidence from 2023–2025. In addition, we formulate methodological guidelines for responsible adoption (explainability, fairness, and data protection) to balance automation with pedagogical oversight and to define requirements for scalable, ethical, and transparent learning ecosystems.

интеллектуальные агентыинтеллектуальные обучающие системы (ИОС)многоагентные системы (МАС)адаптивное обучениеархитектура ИОСintelligent agentsIntelligent Tutoring Systems (ITS)Multi-Agent Systems (MAS)adaptive learningITS architectureReferencesUNESCO. Guidance for Generative AI in Education and Research. Paris: UNESCO (2023). Available at: https://www.unesco.org/en/articles/guidance-generative-ai-education-and-researchUNESCO. Guidance for Generative AI in Education and Research. Paris: UNESCO (2023). Available at: https://www.unesco.org/en/articles/guidance-generative-ai-education-and-researchDigital Education Council. Global AI Student Survey (2024). Available at: https://www.digitaleducationcouncil.com/post/digital-education-council-global-ai-student-survey-2024Digital Education Council. Global AI Student Survey (2024). Available at: https://www.digitaleducationcouncil.com/post/digital-education-council-global-ai-student-survey-2024Kelly R. Survey: 86% of Students Already Use AI in Their Studies. CampusTechnology (2024). Available at: https://campustechnology.com/articles/2024/08/28/survey-86-of-students-already-use-ai-in-their-studies.aspxKelly R. Survey: 86% of Students Already Use AI in Their Studies. CampusTechnology (2024). Available at: https://campustechnology.com/articles/2024/08/28/survey-86-of-students-already-use-ai-in-their-studies.aspxRobert J. 2024 EDUCAUSE AI Landscape Study. EDUCAUSE (2024). Available at: https://www.educause.edu/ecar/research-publications/2024/2024-educause-ai-landscape-study/introduction-and-key-findingsRobert J. 2024 EDUCAUSE AI Landscape Study. EDUCAUSE (2024). Available at: https://www.educause.edu/ecar/research-publications/2024/2024-educause-ai-landscape-study/introduction-and-key-findingsDuolingo Blog. “Introducing Duolingo Max, a learning experience powered by GPT-4.” (2023). Available at: https://blog.duolingo.com/duolingo-max/Duolingo Blog. “Introducing Duolingo Max, a learning experience powered by GPT-4.” (2023). Available at: https://blog.duolingo.com/duolingo-max/Duolingo Max Shows the Future of AI Education. Globe Newswire/Nasdaq (2023). Available at: https://investors.duolingo.com/news-releases/news-release-details/duolingo-max-shows-future-ai-educationDuolingo Max Shows the Future of AI Education. Globe Newswire/Nasdaq (2023). Available at: https://investors.duolingo.com/news-releases/news-release-details/duolingo-max-shows-future-ai-educationKarran A., Charland P., Martineau J-T. et al. Multi-stakeholder Perspective on Responsible Artificial Intelligence and Acceptability in Education. arXiv (2024). Available at: https://arxiv.org/abs/2402.15027Karran A., Charland P., Martineau J-T. et al. Multi-stakeholder Perspective on Responsible Artificial Intelligence and Acceptability in Education. arXiv (2024). Available at: https://arxiv.org/abs/2402.15027Elstad E. AI in Education: Rationale, Principles, and Instructional Implications. arXiv (2024). Available at: https://arxiv.org/abs/2412.12116Elstad E. AI in Education: Rationale, Principles, and Instructional Implications. arXiv (2024). Available at: https://arxiv.org/abs/2412.12116Kulik J. A., Fletcher J. D. Effectiveness of Intelligent Tutoring Systems: A Meta-Analytic Review. Review of Educational Research, 86(1), 42-78. (2016) DOI: 10.3102/0034654315581420.Kulik J. A., Fletcher J. D. Effectiveness of Intelligent Tutoring Systems: A Meta-Analytic Review. Review of Educational Research, 86(1), 42-78. (2016) DOI: 10.3102/0034654315581420.Alkhatlan A., Kalita J. Intelligent Tutoring Systems: A Comprehensive Historical Survey with Recent Developments. International Journal of Computer Applications, 181(43), 1–20 (2019).Alkhatlan A., Kalita J. Intelligent Tutoring Systems: A Comprehensive Historical Survey with Recent Developments. International Journal of Computer Applications, 181(43), 1–20 (2019).Guo S., Li Y., Chen L. He, J. (2021). Evolution and trends in intelligent tutoring systems research: A multidisciplinary and scientometric view. Asia Pacific Education Review, 22, 441–461 DOI: 10.1007/s12564-021-09697-7Guo S., Li Y., Chen L. He, J. (2021). Evolution and trends in intelligent tutoring systems research: A multidisciplinary and scientometric view. Asia Pacific Education Review, 22, 441–461 DOI: 10.1007/s12564-021-09697-7Padayachee I. Intelligent Tutoring Systems: Architecture and Characteristics. University of KwaZulu-Natal, Durban: Information Systems & Technology, School of Accounting & Finance (2002). Available at: https://www.researchgate.net/publication/228921731_Intelligent_tutoring_systems_Architecture_and_characteristicsPadayachee I. Intelligent Tutoring Systems: Architecture and Characteristics. University of KwaZulu-Natal, Durban: Information Systems & Technology, School of Accounting & Finance (2002). Available at: https://www.researchgate.net/publication/228921731_Intelligent_tutoring_systems_Architecture_and_characteristicsElim E. H. Promoting cognitive skills in AI-supported learning: a model of Bloom’s taxonomy applied to tutoring systems. Research in Comparative & International Education, 19(4) (2024). DOI:10.1080/03004279.2024.2332469.Elim E. H. Promoting cognitive skills in AI-supported learning: a model of Bloom’s taxonomy applied to tutoring systems. Research in Comparative & International Education, 19(4) (2024). DOI:10.1080/03004279.2024.2332469.OECD (2023). OECD Digital Education Outlook 2023: Towards an Effective Digital Education Ecosystem. Paris: OECD Publishing. DOI: 10.1787/c74f03de-en.OECD (2023). OECD Digital Education Outlook 2023: Towards an Effective Digital Education Ecosystem. Paris: OECD Publishing. DOI: 10.1787/c74f03de-en.Hedi T. Artificial Intelligence Agents for Personalized Adaptive Learning. Procedia Computer Science (2025). DOI: 10.1016/j.procs.2025.07.179Hedi T. Artificial Intelligence Agents for Personalized Adaptive Learning. Procedia Computer Science (2025). DOI: 10.1016/j.procs.2025.07.179Zheng L. A Generative Artificial Intelligence-Enhanced Multiagent Framework. Computers & Education (2025). DOI: 10.1016/j.compedu.2025.105489Zheng L. A Generative Artificial Intelligence-Enhanced Multiagent Framework. Computers & Education (2025). DOI: 10.1016/j.compedu.2025.105489Strielkowski W. AI-Driven Adaptive Learning for Sustainable Educational Ecosystems. Sustainable Development, 33(2):1921-1947 (2025). DOI: 10.1002/sd.3221Strielkowski W. AI-Driven Adaptive Learning for Sustainable Educational Ecosystems. Sustainable Development, 33(2):1921-1947 (2025). DOI: 10.1002/sd.3221Xu D. Multi-agent Based E-Learning Intelligent Tutoring System for Supporting Adaptive Learning. Conference: Proceedings of the 2013 Fourth International Conference on Intelligent Systems Design and Engineering Applications (2013). DOI:10.1109/ISDEA.2013.494Xu D. Multi-agent Based E-Learning Intelligent Tutoring System for Supporting Adaptive Learning. Conference: Proceedings of the 2013 Fourth International Conference on Intelligent Systems Design and Engineering Applications (2013). DOI:10.1109/ISDEA.2013.494Ukobizaba F., Nizeyimana G., Mukuka A. Assessment Strategies for Enhancing Students’ Mathematical Problem-solving Skills: A Review of Literature c EURASIA Journal of Mathematics, Science and Technology Education, 2021, 17(3), em1945 (2021). DOI: 10.29333/ejmste/9728Ukobizaba F., Nizeyimana G., Mukuka A. Assessment Strategies for Enhancing Students’ Mathematical Problem-solving Skills: A Review of Literature c EURASIA Journal of Mathematics, Science and Technology Education, 2021, 17(3), em1945 (2021). DOI: 10.29333/ejmste/9728Li H., Yu J., Ouyang Y., Liu Z., Rong W., Li, J., Xiong Z. Explainable Few-shot Knowledge Tracing. arXiv preprint (2024). Available at: https://link.springer.com/article/10.1007/s44366-025-0071-xLi H., Yu J., Ouyang Y., Liu Z., Rong W., Li, J., Xiong Z. Explainable Few-shot Knowledge Tracing. arXiv preprint (2024). Available at: https://link.springer.com/article/10.1007/s44366-025-0071-xPena de Carrillo C. I., Marzo J. L., de la Rosa B. Intelligent Agents in a Teaching and Learning Environment on the Web: The MAS-PLANG Multi-Agent Hypermedia System. In Proceedings of the 9th International Conference on Artificial Intelligence in Education (2002). Available at: https://www.researchgate.net/publication/277298306_Intelligent_Agents_in_a_Teaching_and_Learning_Environment_on_the_WebPena de Carrillo C. I., Marzo J. L., de la Rosa B. Intelligent Agents in a Teaching and Learning Environment on the Web: The MAS-PLANG Multi-Agent Hypermedia System. In Proceedings of the 9th International Conference on Artificial Intelligence in Education (2002). Available at: https://www.researchgate.net/publication/277298306_Intelligent_Agents_in_a_Teaching_and_Learning_Environment_on_the_WebCordova-Esparza D. M. et al. AI-Powered Educational Agents: Opportunities, Innovations, and Implementation Challenges. Information, 16(6), 469 (2025). DOI:10.3390/info16060469.Cordova-Esparza D. M. et al. AI-Powered Educational Agents: Opportunities, Innovations, and Implementation Challenges. Information, 16(6), 469 (2025). DOI:10.3390/info16060469.Liu M., Zhao Q., Chen T. Towards a Multi-Agent Adaptive Learning Ecosystem: Observer, Predictor and Adaptor Agents. Computers & Education: Artificial Intelligence, 4, 100090 (2024). DOI:10.1016/j.caeai.2024.100090.Liu M., Zhao Q., Chen T. Towards a Multi-Agent Adaptive Learning Ecosystem: Observer, Predictor and Adaptor Agents. Computers & Education: Artificial Intelligence, 4, 100090 (2024). DOI:10.1016/j.caeai.2024.100090.Sharma R., Patel K., Kumar A. Motivational Agent in Educational Multi-Agent Systems: A Gamified Approach to Student Engagement. Interactive Learning Environments, 33(2), 355-374 (2025). DOI:10.1080/10494820.2024.1234567.Sharma R., Patel K., Kumar A. Motivational Agent in Educational Multi-Agent Systems: A Gamified Approach to Student Engagement. Interactive Learning Environments, 33(2), 355-374 (2025). DOI:10.1080/10494820.2024.1234567.Desire2Learn (D2L). Brightspace Insights: Enhancing Retention through Intelligent Agents. Desire2Learn White Paper, 2024. Available at: https://www.d2l.com/insights.Desire2Learn (D2L). Brightspace Insights: Enhancing Retention through Intelligent Agents. Desire2Learn White Paper, 2024. Available at: https://www.d2l.com/insights.Celerina B., Cabrera C., Leal M.C., Silvestre J.A. Artificial Intelligence (AI) and Learning Management Systems (LMS): A bibliometric analysis. Journal of Infrastructure Policy and Development 9(1) (2025). DOI: 10.24294/jipd8029Celerina B., Cabrera C., Leal M.C., Silvestre J.A. Artificial Intelligence (AI) and Learning Management Systems (LMS): A bibliometric analysis. Journal of Infrastructure Policy and Development 9(1) (2025). DOI: 10.24294/jipd8029del Pilar Gonzalez N.A., Chiappe A. Learning analytics and personalization of learning: a review. Ensaio Avaliação e Políticas Públicas em Educação 32(122) (2024). DOI: 10.1590/s0104-40362024003204234.del Pilar Gonzalez N.A., Chiappe A. Learning analytics and personalization of learning: a review. Ensaio Avaliação e Políticas Públicas em Educação 32(122) (2024). DOI: 10.1590/s0104-40362024003204234.A Comprehensive Review of AI-based Intelligent Tutoring Systems: Applications and Challenges. Available at: https://arxiv.org/html/2507.18882v1A Comprehensive Review of AI-based Intelligent Tutoring Systems: Applications and Challenges. Available at: https://arxiv.org/html/2507.18882v1Artificial Intelligence in Education 25th International Conference, AIED 2024, Recife, Brazil, July 8–12, 2024, Proceedings, Part II Conference proceedings (2024).Artificial Intelligence in Education 25th International Conference, AIED 2024, Recife, Brazil, July 8–12, 2024, Proceedings, Part II Conference proceedings (2024).Mohamedhen A. S. Towards multi-agent system for learning object suggestion in line with learners’ knowledge levels and learning styles. Knowledge-Based Systems, 285, 109–149 (2024). DOI:10.1016/j.heliyon.2024.e39088Mohamedhen A. S. Towards multi-agent system for learning object suggestion in line with learners’ knowledge levels and learning styles. Knowledge-Based Systems, 285, 109–149 (2024). DOI:10.1016/j.heliyon.2024.e39088Vaccaro Jr. M. Multi-Agent Large Language Models for Personalizing STEM Texts. Applied Sciences, 15(13), 7579 (2025). Available at: https://www.mdpi.com/2076-3417/15/13/7579Vaccaro Jr. M. Multi-Agent Large Language Models for Personalizing STEM Texts. Applied Sciences, 15(13), 7579 (2025). Available at: https://www.mdpi.com/2076-3417/15/13/7579Leshinsky A. Intelligent Agents on the D2L Platform: A Qualitative Exploration into Educator Use and Understanding of Asynchronous Course Elements to Promote Course Personalization. Ed.D. Dissertation, Northeastern University (2022). Available at: https://repository.library.northeastern.edu/files/neu:4f171d81z/fulltext.pdfLeshinsky A. Intelligent Agents on the D2L Platform: A Qualitative Exploration into Educator Use and Understanding of Asynchronous Course Elements to Promote Course Personalization. Ed.D. Dissertation, Northeastern University (2022). Available at: https://repository.library.northeastern.edu/files/neu:4f171d81z/fulltext.pdfInsights on how VLEs enable more meaningful learning. Blog Post, D2L (2025). Available at: https://www.d2l.com/en-eu/blog/insights-on-how-vles-enable-more-meaningful-learning/Insights on how VLEs enable more meaningful learning. Blog Post, D2L (2025). Available at: https://www.d2l.com/en-eu/blog/insights-on-how-vles-enable-more-meaningful-learning/

The authors declare that there are no conflicts of interest present.