Abstract

The educational technology market continues to expand, yet most learning management systems remain content-centric, weakly personalized, and reactive to failure. This paper presents Lumina, a privacy-first, multi-agent adaptive learning management system that combines Bayesian Knowledge Tracing (BKT), Deep Knowledge Tracing (DKT), reinforcement learning (RL) for curriculum sequencing, retrieval-augmented generation (RAG), and a behavior engine that captures more than fifty passive learning signals. Lumina coordinates six specialized agents through the Model Context Protocol to provide closed-loop tutoring, assessment, intervention, analytics, and governance. The evaluation is organized into three complementary layers: prototype stress testing across 10,000 synthetic learner scenarios, external validation on the public xAPI-Edu-Data benchmark (480 learner records), and a reproducible benchmark matrix defined for future knowledge-tracing studies on ASSISTments and EdNet. The prototype analytics benchmark completed in 0.90 seconds with zero runtime failures and a throughput of approximately 11,051 inference runs per second. On xAPI-Edu-Data, a Random Forest baseline achieved 0.800 accuracy and 0.804 macro-F1 under five-fold stratified cross-validation, demonstrating that the behavioral signal families used by Lumina are predictive on real educational data. These results position Lumina as a technically coherent, self-hosted, and benchmark-ready foundation for explainable personalized education.

References

• HolonIQ, "Global EdTech Market to Reach $404B by 2025," HolonIQ Research Report, 2024.
• K. Jordan, "Massive open online course completion rates revisited: Assessment, length and attrition," International Review of Research in Open and Distributed Learning, vol. 21, no. 3, pp. 1–29, 2020.
• Association for Talent Development, "State of the Industry Report," ATD Research, 2023.
• M. Kerres, "Against All Odds: A Systematic Review of Outcomes and Success Factors for Online Learning," Frontiers in Education, vol. 6, 2021.
• R. S. Baker and A. Inventado, "Educational Data Mining and Learning Analytics," in Learning Analytics, Springer, 2022, pp. 61–75.
• W. Pelgrum and R. Plomp, "The IEA Study of Computers in Education: Implementation of an Innovation in 21 Education Systems," International Association for the Evaluation of Educational Achievement, 2020.
• National Association of Colleges and Employers, "Job Outlook Survey," NACE Research Report, 2024.
• C. Romero and S. Ventura, "Educational data mining and learning analytics: An updated survey," WIREs Data Mining and Knowledge Discovery, vol. 10, no. 3, 2020.
• National Education Association, "Survey: Educator Burnout and COVID-19," NEA Research, 2022.
• B. Settles and B. Meeder, "A Trainable Spaced Repetition Model for Language Learning," in Proc. ACL, 2016, pp. 1848–1858.
• S. Ritter, J. Anderson, K. Koedinger, and A. Corbett, "Cognitive Tutor: Applied Research in Mathematics Education," Psychonomic Bulletin and Review, vol. 14, no. 2, pp. 249–255, 2019.
• P. Prinsloo, "Data frontiers and frontiers of power in (higher) education," Teaching in Higher Education, vol. 25, no. 4, pp. 434–450, 2020.
• J. Stamper and Z. Pardos, "The Rise and Fall of Knewton: Lessons for Adaptive Learning," Educational Technology Research and Development, vol. 69, pp. 2365–2383, 2021.
• A. T. Corbett and J. R. Anderson, "Knowledge Tracing: Modeling the Acquisition of Procedural Knowledge," User Modeling and User-Adapted Interaction, vol. 4, no. 4, pp. 253–278, 1994.
• Z. A. Pardos and N. T. Heffernan, "Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing," in Proc. UMAP, 2010, pp. 255–266.
• C. Piech et al., "Deep Knowledge Tracing," in Advances in Neural Information Processing Systems (NeurIPS), vol. 28, 2015.
• J. Zhang, X. Shi, I. King, and D. Yeung, "Dynamic Key-Value Memory Networks for Knowledge Tracing," in Proc. WWW, 2017, pp. 765–774.
• K. VanLehn, "The Relative Effectiveness of Human Tutoring, Intelligent Tutoring Systems, and Other Tutoring Systems," Educational Psychologist, vol. 46, no. 4, pp. 197–221, 2011.
• A. C. Graesser et al., "AutoTutor: An Intelligent Tutoring System with Mixed-Initiative Dialogue," IEEE Transactions on Education, vol. 48, no. 4, pp. 612–618, 2005.
• M. Wooldridge and N. R. Jennings, "Intelligent Agents: Theory and Practice," The Knowledge Engineering Review, vol. 10, no. 2, pp. 115–152, 1995.
• J. S. Park et al., "Generative Agents: Interactive Simulacra of Human Behavior," in Proc. UIST, 2023.
• Anthropic, "Model Context Protocol Specification," Technical Documentation, 2024.
• B. McMahan et al., "Communication-Efficient Learning of Deep Networks from Decentralized Data," in Proc. AISTATS, 2017.
• UNESCO, "Guidance for Generative AI in Education and Research," UNESCO Publications, 2023.
• U.S. Department of Education, "Artificial Intelligence and the Future of Teaching and Learning," Office of Educational Technology, 2023.
• UNESCO, "Less than 10% of Schools and Universities Have Formal Guidance on AI," UNESCO Survey Report, 2024.
• M. Seligman, "Flourish: A Visionary New Understanding of Happiness and Well-being," Free Press, 2021.
• OECD, "OECD Digital Education Outlook 2023," OECD Publishing, 2023.
• A. Tsai et al., "Retrieval Practice Consistently Benefits Student Learning: A Systematic Review," Educational Psychology Review, vol. 33, pp. 1423–1451, 2021.
• I. Aljarah, "xAPI-Edu-Data," Kaggle dataset, 2016.
• Y. Choi, Y. Lee, J. Cho, J. Baek, B. Kim, and J. Heo, "EdNet: A Large-Scale Hierarchical Dataset in Education," in Proc. Int. Conf. Educational Data Mining (EDM), 2020.
• S. Pandey and G. Karypis, "A Self-Attentive Model for Knowledge Tracing," arXiv:1907.06837, 2019.