Intelligent and Adaptive Systems

Intelligent and adaptive systems support the personalisation of the learning process by tailoring learning content based on the needs of learners in order to create personalised learning experiences. These systems can automate aspects of the learning process or recommend personalised learning experiences for learners. They use different methods to achieve this, such as agent-based or multi-agent models, recommender systems that provide personalised materials and resources, and adaptive systems that are integrated with various technologies, methods, and techniques to enable personalisation functionalities.

Intelligent agent systems are autonomous AI-based systems (intelligent algorithms) that tailor educational experiences to individual learner needs and can assist in predicting learners’ preferences or requirements. They use different models or agents to achieve personalisation, with each model providing a specific function, such as a user (learner) model or a pedagogical model. These systems include Intelligent Tutoring Systems (ITS), multi-agent systems (e.g., student agents, teacher agents), and chatbots.

Examples of intelligent systems:

  • IBM Watson Tutor
  • Socratic by Google – an AI learning app that helps students solve problems by scanning questions and providing step-by-step explanations.
  • MagicSchool.ai
  • Eduaide.AI
  • Carnegie Learning MATHia – an intelligent tutoring system that provides personalised mathematics instruction and real-time feedback.
  • Khanmigo (Khan Academy) – an AI-powered tutor that provides personalised learning support and Socratic-style guidance for students.

Resources

References

  • Aleven, V., Sewall, J., Andres, J. M., Sottilare, R., Long, R., & Baker, R. (2018). Towards adapting to learners at scale: Integrating MOOC and intelligent tutoring frameworks. In Proceedings of the 5th Annual ACM Conference on Learning at Scale (L@S 2018).
  • Burov, O. Y., Pasko, N., Viunenko, O. B., Agadzhanova, S. V., & Ahadzhanov-Honsales, K. (2024). Using intelligent agent-managers to build personal learning environments in the e-learning system. In AREdu (pp. 125–133).
  • Córdova-Esparza, D. M. (2025). AI-powered educational agents: Opportunities, innovations, and ethical challenges. Information, 16(6), 469.
  • De Meo, P., Garro, A., Terracina, G., & Ursino, D. (2007). Personalizing learning programs with X-Learn, an XML-based “user-device” adaptive multi-agent system. Information Sciences, 177(8), 1729–1770. https://doi.org/10.1016/j.ins.2006.11.001
  • Graesser, A. C., Hu, X., & Sottilare, R. (2018). Intelligent tutoring systems. In International Handbook of the Learning Sciences (pp. 246–255). Routledge. https://doi.org/10.4324/9781315617572-24
  • Greer, J., & Mark, M. (2016). Evaluation methods for intelligent tutoring systems revisited. International Journal of Artificial Intelligence in Education, 26(1), 387–392. https://doi.org/10.1007/s40593-015-0043-2
  • Hedi, T., Nouzri, S., Mualla, Y., & Abbas-Turki, A. (2025). Artificial intelligence agents for personalized adaptive learning. Procedia Computer Science, 265, 252–259.
  • Kulik, J. A., & Fletcher, J. D. (2016). Effectiveness of intelligent tutoring systems: A meta-analytic review. Review of Educational Research, 86(1), 42–78.
  • Laeeq, K., & Memon, Z. A. (2019). Scavenge: An intelligent multi-agent based voice-enabled virtual assistant for LMS. Interactive Learning Environments, 1–19.
  • Phillips, A., Pane, J. F., Reumann-Moore, R., & Shenbanjo, O. (2020). Implementing an adaptive intelligent tutoring system as an instructional supplement. Educational Technology Research and Development, 68(3), 1409–1437.
  • Shih, S. C., Chang, C. C., Kuo, B. C., & Huang, Y. H. (2023). Mathematics intelligent tutoring system for learning multiplication and division of fractions based on diagnostic teaching. Education and Information Technologies, 28(7), 9189–9210.
  • vanLehn, K. (2011). The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educational Psychologist, 46(4), 197–221.

Recommender systems are technologies that use artificial intelligence, machine learning, and data analytics to predict or suggest tailored learning content (such as courses and materials), educational pathways, and pacing based on individual learning needs. For example, they analyse learner characteristics such as preferences, past performance, and learning styles to generate personalised suggestions and recommendations, including learning content, resources, activities, and feedback.

There are different types of recommendation systems, including collaborative filtering, which uses similarities between users and their interests to recommend items, and content-based filtering, which recommends items based on similarities between the items themselves. The following list presents different types of recommended systems that can be used to create personalised learning process.

  • Content-based recommendation techniques
  • Collaborative filtering-based recommendation techniques
  • Knowledge-based recommendation techniques
  • Hybrid recommendation techniques

These systems also include features such as data mining, prediction, and pattern identification.

Examples of technologies and applications include:

  • Gradescope – an AI-assisted grading platform that automates marking and provides structured feedback for assignments and exams.
  • Diffit – an AI-powered educational tool that helps teachers create differentiated learning materials by automatically adapting texts and resources to different reading levels and learner needs.
  • MagicSchool AI – an AI-driven platform that supports educators by generating lesson plans, assessments, teaching resources, and personalised learning materials to enhance classroom instruction.

References

  • Gm, D., Goudar, R. H., Kulkarni, A. A., Rathod, V. N., & Hukkeri, G. S. (2024). A digital recommendation system for personalized learning to enhance online education: A review. IEEE Access, 12, 34019–34041.
  • Plirdpring, P., & Songsangyos, P. (2025). Recommendation system for personalized lesson learning. TPM–Testing, Psychometrics, Methodology in Applied Psychology, 32(2), 753–760.
  • Syed, T. A., Palade, V., Iqbal, R., & Nair, S. S. K. (2017, November). A personalized learning recommendation system architecture for learning management system. In Proceedings of KDIR (pp. 275–282).
  • Tatineni, S. (2020). Recommendation systems for personalized learning: A data-driven approach in education. Journal of Computer Engineering and Technology (JCET), 4(2), 18–31.

The advancement of data-driven technologies and intelligent systems has led to the transformation of traditional learning management systems into adaptive systems that provide personalisation capabilities to deliver tailored learning materials and experiences based on learners’ needs. These systems integrate built-in technologies that combine different tools and techniques to support personalised learning experiences. They adjust content, pacing, and learning paths based on each individual’s characteristics such as performance and preferences.

Adaptive learning platforms utilise technologies such as big data, machine learning, and artificial intelligence (AI) to assess learners’ knowledge and dynamically adjust content to help them master the skills and concepts presented in a lesson. These platforms also integrate machine learning, natural language processing, and predictive analytics to collect and analyse data, and apply the results in practice.

Unlike traditional platforms, adaptive learning platforms leverage AI and data analytics to personalise content for each learner.

Some adaptive systems are commercially available or offered through subscription services and can be readily adopted within learning environments. Examples include:

  • Quizizz AI – an adaptive learning platform that generates quizzes and personalised practice activities based on learner performance.
  • Century Tech – an AI-powered learning platform that adapts content and learning pathways based on student performance and knowledge gaps.

Resources

References

  • Tan, L. Y., Hu, S., Yeo, D. J., & Cheong, K. H. (2025). Artificial intelligence-enabled adaptive learning platforms: A review. Computers and Education: Artificial Intelligence, 9, 100429.
  • Essa, S., Human-Hendricks, N. E., & Celik, T. (2025). A personalised adaptive e-learning system based on deep learning approaches: A critical interpretation of learning style models. South African Journal of Higher Education, 39(6), 135–157.
  • Edwards, M., Johnson, D., Ford, C., Pugliese, L., Fritz, J., & Birk, S. (2017). From adaptive to adaptable: The next generation for personalized learning. IMS Global Learning Consortium.
🤖 Use the integrated AI to get personalised feedback!