A distributed multi-agent framework for adaptive personalized online learning with dynamic knowledge graphs and learner modeling
,
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
A distributed multi-agent framework is developed to enhance adaptive personalized online learning. The framework integrates Large Language Models (LLMs), a Dynamic Educational Knowledge Graph (DEKG), Knowledge Tracing (KT), Reinforcement Learning (RL), and Explainable Artificial Intelligence (XAI) to support learner modeling, adaptive recommendation, and explanation. The architecture separates learner-facing interaction from distributed domain processing while enabling coordinated knowledge representation and adaptive decision-making. A controlled simulation-based feasibility study evaluates learner-state estimation and personalized recommendation. The results show that graph-enhanced KT provides a modest improvement over the independent KT baseline, while the graph-aware RL policy achieves the highest final mastery and mastery gain among the evaluated strategies, although its advantage does not extend to every evaluation metric. The findings also indicate that recommendation performance is influenced by reward design. Overall, the simulation provides preliminary evidence of the feasibility of the proposed framework. Further evaluation using real educational datasets and learner interactions is required to assess its effectiveness and generalizability.
Article Details
Conflict of Interest
© 2026 The authors. This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License.
References
Abu-Rasheed, H., Jumbo, C., Al Amin, R., Weber, C., Wiese, V., Obermaisser, R., & Fathi, M. (2025). LLM-assisted knowledge graph completion for curriculum and domain modelling in personalized higher education recommendations. In 2025 IEEE Global Engineering Education Conference (EDUCON) (pp. 1–5). IEEE. https://doi.org/10.1109/EDUCON62633.2025.11016377
Bian, H. (2025). LLM-empowered knowledge graph construction: A survey. ICAIS 2025. https://arxiv.org/abs/2510.20345
Bordes, A., Usunier, N., García-Durán, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems (Vol. 26, pp. 2787–2795). https://proceedings.neurips.cc/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html
Cheng, K., Peng, L., Wang, P., Ye, J., Sun, L., & Du, B. (2024). DyGKT: Dynamic graph learning for knowledge tracing. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 409–420). Association for Computing Machinery. https://doi.org/10.1145/3637528.3671773
Fu, Z. (2025). Integrating reinforcement learning with dynamic knowledge tracing for personalized learning path optimization. Scientific Reports, 15(1), Article 40202. https://doi.org/10.1038/s41598-025-23900-4
Gronauer, S., & Diepold, K. (2022). Multi-agent deep reinforcement learning: A survey. Artificial Intelligence Review, 55, 895–943. https://doi.org/10.1007/s10462-021-09996-w
Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998). Planning and acting in partially observable stochastic domains. Artificial Intelligence, 101(1–2), 99–134.
https://doi.org/10.1016/S0004-3702(98)00023-X
Liu, F., Wang, Y., Feng, Q., Zhu, L., & Li, G. (2024). Optimizing e-learning environments: Leveraging large language models for personalized education pathways. In Proceedings of the 5th International Conference on Education, Knowledge and Information Management (pp. 811–817). Atlantis Press. https://doi.org/10.2991/978-94-6463-502-7_86
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (Vol. 30, pp. 4765–4774). https://papers.nips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html
Magar, S. P., Kumar, M. V., Manjula, B. M., & Gudala, L. (2025). Reinforcement learning with knowledge graphs for personalized news recommendation. ITM Web of Conferences, 79, Article 01039. https://doi.org/10.1051/itmconf/20257901039
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533. https://doi.org/10.1038/nature14236
Nguyen, T., & Nguyen, N. G. (2026). Enhancing knowledge tracing with persistent long-term memory via the Model Context Protocol. In Lecture Notes in Networks and Systems (Vol. 1988, pp. 400–410). Springer. https://doi.org/10.1007/978-3-032-26898-3_36
Nguyen, T., Do, D., Vi, H., Vo, K. T., Ta, T.-T., Nguyen, P., Nguyen, H.-T., & Nguyen-Hoang, T.-A. (2025). HetGNN-KGAT: Enhancing personalized course recommendation in MOOCs with knowledge graph attention networks. IEEE Access, 13, 192045–192068. https://doi.org/10.1109/ACCESS.2025.3630894
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L. J., & Sohl-Dickstein, J. (2015). Deep knowledge tracing. In Advances in Neural Information Processing Systems (Vol. 28, pp. 505–513). https://proceedings.neurips.cc/paper/2015/hash/bac9162b47c56fc8a4d2a519803d51b3-Abstract.html
Rasheed, H. A., Weber, C., & Fathi, M. (2024). Knowledge graphs as context sources for LLM-based explanations of learning recommendations. arXiv. https://arxiv.org/abs/2403.03008
Shen, Y., & Chen, Y. (2025). Knowledge tracing enhanced by graph convolutional networks with self-supervised learning. International Journal of Information and Communication Technology Education, 21(1), 1–22. https://doi.org/10.4018/IJICTE.385130
Shiferaw, N. A., Leandre, S. H., Sinha, A., & Rout, D. (2024). BERT-based approach for automating course articulation matrix construction with explainable AI. arXiv. https://doi.org/10.48550/arXiv.2411.14254
Sun, Z., Deng, Z.-H., Nie, J.-Y., & Tang, J. (2019). RotatE: Knowledge graph embedding by relational rotation in complex space. In 7th International Conference on Learning Representations (ICLR 2019). https://openreview.net/forum?id=HkgEQnRqYQ
Wang, Y., Wei, T., Li, Q., & Zeng, L. (2026). Beyond static question banks: Dynamic knowledge expansion via LLM-automated graph construction and adaptive generation. arXiv. https://arxiv.org/abs/2602.00020
Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8, 279–292. https://doi.org/10.1007/BF00992698
Wong, A., Bäck, T., Kononova, A. V., & Plaat, A. (2023). Deep multiagent reinforcement learning: Challenges and directions. Artificial Intelligence Review, 56, 5023–5056. https://doi.org/10.1007/s10462-022-10299-x
Wu, H., Zhong, X., & Yuan, J. (2025). Textbook2KG: Decoding knowledge graph from very long textual content via prompt engineering. In 2025 International Conference on Artificial Intelligence and Digital Ethics (ICAIDE). IEEE. https://doi.org/10.1109/ICAIDE65466.2025.11189379
Zhou, L.-Y., & Wang, Y.-Y. (2025). Simulation of personalized English learning path recommendation system based on knowledge graph and deep reinforcement learning. Scientific Reports, 15(1), Article 34554. https://doi.org/10.1038/s41598-025-17918-x