The Adaptive Innovative Pedagogical Architecture(AIPA–SIM): A Multi AgentSimulation Study on Teaching Method Management
DOI:
https://doi.org/10.19109/tadrib.v11i2.32548Keywords:
Adaptive learning, Multi-agent simulation, Pedagogical architecture, Educational innovation, teaching method managementAbstract
The digital transformation in education requires an adaptive and innovative pedagogical architecture to effectively manage teaching methods. Traditional learning systems often fail to adjust instructional strategies to individual learners’ needs. Therefore, this study developed the Adaptive Innovative Pedagogical Architecture (AIPA–SIM), a multi-agent simulation model designed to analyze the dynamics of adaptive teaching method management. This study employed a simulation-based experimental design with three learning system scenarios: non-adaptive, semi-adaptive, and fully adaptive. The model was developed using NetLogo 6.3.0 and Python Mesa Framework, incorporating teacher, student, and system agents. Key parameters included Learning Performance, Adaptivity Rate, Engagement Index, and System Efficiency. Data were analyzed using ANOVA and Tukey HSD tests to compare system performance. Simulation results revealed that the fully adaptive system (AIPA–SIM) significantly improved learning performance (+29.5%) compared to the non-adaptive system (p < 0.01). The Engagement Index reached 0.92 and System Efficiency achieved 93.7, indicating high responsiveness to students’ behavioral changes. A strong positive correlation (r = 0.88) was observed between adaptivity level and learning performance. The AIPA–SIM model proved effective as an adaptive pedagogical architecture capable of enhancing learning outcomes through automated, agent-based decision-making mechanisms. This research provides both conceptual and practical contributions to the development of smart adaptive learning systems and data-driven educational policies in the digital era.
References
Assagaf, G., et al. (2025). Effectiveness of flipped classroom model on minimizing learning gaps: meta-analytic perspectives. Journal of Digital & Distance Learning (meta-analysis).
Banihashem, S. K., et al. (2022). A systematic review of the role of learning analytics to improve feedback practices in technology-mediated learning environments. Computers & Education.
Banihashem, S. K., & colleagues. (2024). Learning analytics for online game-based learning: A systematic synthesis. Behaviour & Information Technology / Taylor & Francis.
Banihashem, S. K., et al. (2024). The impact of learning analytics-based feedback interventions in online learning environments. International Review of Research in Open and Distributed Learning (IRRODL).
Chen, J., et al. (2023). NetLogo AR and pedagogical applications: augmenting agent-based learning with real-world environments. CCL / technical report.
Chen, F., et al. (2025). Learning analytics in inquiry-based learning: Systematic review. Educational Technology Research and Development (review).
Collins, B., et al. (2023). Using NetLogo to build an agent-based model for teaching and research. AETR Journal (paper/technical report).
de La Hoz-Ruiz, J., et al. (2024). Learning analytics for enhanced teachers’ professional capital: A systematic review. Frontiers in Psychology.
Fitriyah, I. M., et al. (2022). Problem-based learning trends 2010–2020: meta-analysis and implications for higher education. Journal of Physics: Conference Series (review paper).
Fu, S., et al. (2022). A reinforcement learning-based smart educational environment for higher education. IGI Global (book chapter / article on RL in smart classrooms).
Gao, C., Lan, X., Li, N., Yuan, Y., Ding, J., Zhou, Z., Xu, F., & Li, Y. (2024). Large language models empowered agent-based modeling and simulation: A survey and perspectives. Humanities and Social Sciences Communications. (Survey article on LLMs + ABM).
Hocine, N., et al. (2025). Systematic literature review: Employing AI in adaptive learning recommendation systems for vocational education. SCITEPRESS (review paper).
Outay, F., et al. (2024). Multi-agent system-based framework for an intelligent competency management environment. Smart Learning Environments.
Outay, F., & colleagues (2024). Enhancing educational practices with multi-agent systems: review and design patterns. Research chapter / conference proceedings (comprehensive review).
Kou, L., et al. (2020). Multi-agent-based modelling and simulation for complex socio-technical systems. Applied Mathematical Modelling / Elsevier.
Li, X., et al. (2022). Agent-based modeling and simulation of digital learning environments. Conference proceedings (ED-tech / AIED / LAK).
Lorig, F., Belfrage, M., & Johansson, E. (2024). Teaching agent-based modeling for simulating social systems: A problem-based learning approach. MABS Workshop paper.
Martin, F., et al. (2020). Adaptive learning technologies: pedagogical foundations and impacts. European Journal of Education / review (2020–2021 coverage).
Memarian, B., et al. (2024). A scoping review of reinforcement learning in education. Computers & Education: Artificial Intelligence / Elsevier (scoping review).
Mielke, A., Murphy, N., & Carsey, T. (2023). Modeling and simulation in graduate education: NetLogo applications and teaching. AETR/education methods (technical / pedagogical article).
Mishra, S., et al. (2025). Agent-based modeling: Insights into consumer (and learner) behavior and complex systems. Simulation Modelling Practice and Theory (review/chapter).
Mon, B. F. (2023). Reinforcement learning in education: A literature review. Informatics / MDPI (review article on RL applications in education).
Muñoz, J. L. R., Ojeda, F. M., Jurado, D. L. A., Peña, P. F. P., Carranza, C. P. M., Berríos, H. Q., & Vasquez-Pauca, M. J. (2022). Systematic review of adaptive learning technology for learning in higher education. Eurasian Journal of Educational Research, 98: 221–233.
NetLogo Development Team. (2023). NetLogo AR: Bringing room-scale real-world environments to agent-based modelling (J. Chen, tech. report). Center for Connected Learning and Computer-Based Modeling (CCL), Northwestern University.
Ngulube, P., & Ncube, M. M. (2025). Leveraging learning analytics to improve the user experience of learning management systems. Information (MDPI).
Osakwe, I., et al. (2024). Towards prescriptive analytics of self-regulated learning using reinforcement learning approaches. British Journal of Educational Technology.
Riedmann, A., et al. (2025). Reinforcement learning in education: Systematic review and best practices. International Journal of Artificial Intelligence in Education (Springer).
Strelan, P., et al. (2020). The flipped classroom: A meta-analysis of effects on student performance. Computers & Education (meta-analysis).
Vulic, J., Jacobson, M. J., & Levin, J. A. (2024). Exploring education as a complex system: Computational educational research with multi-level agent-based modeling. Education Sciences. 14(5): 551.
Wooldridge, M. (Ed.). (2022). Multi-Agent-Based Simulation XXII (Proceedings, MABS / AAMAS). Springer.
