🧠 AI Ed Wiki

📄 Research Article

Simulating Learners' Task-Selection Strategies and System Constraints in Mastery Learning

● high · 2026-05-22intelligent-tutoring, mastery-learning, adaptive-learning, engagement-metrics, simulation, k-12, student-experience, adaptive-learning-systems, llm, knowledge-tracing

Intelligent Tutoring Systems often grant learners shared control over skill and problem selection. We propose a simulation-based framework to examine how learner task-selection strategies and system constraints shape mastery learning efficiency.

This paper introduces a simulation-based framework for evaluating how learner task-selection strategies interact with mastery learning algorithms in Intelligent Tutoring Systems. Using interaction data from 261 students across two mathematical domains (equation solving and graph interpretation), the authors simulate strategies including Weakness Targeting and Interleaving, measuring overpractice as an efficiency metric. Risk-averse strategies produced substantially higher overpractice, especially for complex multi-step problems. Critically, targeted system constraints significantly reduced inefficiencies for maladaptive strategies while minimally affecting already efficient strategies. This provides a low-cost methodology for pre-testing algorithmic constraints before classroom deployment. The findings extend Engagement Forecasting ITS by exploring the behavioral mechanisms behind engagement patterns, and complement Adaptive Learning research by quantifying how learner autonomy interacts with system optimization. The simulation methodology aligns with Neural Symbolic Knowledge Tracing approaches that model learner behavior patterns, while the focus on mastery learning efficiency connects to GenAI Tutor Engagement Patterns research on how different student behaviors shape tutoring outcomes. The finding that constraints can correct maladaptive behaviors without penalizing efficient learners has implications for LLM Student Modeling Memory architectures that could incorporate task-selection preferences into student models.

Connected Concepts

  • Adaptive Learning

    • Connected Articles

  • Engagement Forecasting ITS
  • Neural Symbolic Knowledge Tracing
  • GenAI Tutor Engagement Patterns
  • LLM Student Modeling Memory

    • Citation

    Haley Noh, Aarna Chowdhary, Jeroen Ooge, Vincent Aleven, Conrad Borchers (2026). Simulating Learners' Task-Selection Strategies and System Constraints in Mastery Learning. arXiv:2605.21613. EDM 2026 (short paper).