Future-Proofing Programmers: Optimal Knowledge Tracing for AI-Assisted Personalized Education

2025-09-28

AI Summary

Conventional educational tools exhibit limitations in modeling learners’ cognitive states, delivering adaptive feedback, and generating pedagogically sound learning strategies. Method: We propose CoTutor, an AI-driven tutoring framework that innovatively integrates Bayesian Knowledge Tracing (BKT) with signal processing techniques and employs convex optimization to enhance the accuracy and robustness of latent state estimation. Furthermore, it couples generative AI to produce interpretable, personalized feedback and dynamically recommend adaptive learning pathways. Contribution/Results: (1) We introduce the first learning modeling framework that simultaneously enables automated analysis, preserves expert pedagogical judgment, and ensures privacy compliance. (2) In a university-level programming course, CoTutor significantly improved learning outcomes (p < 0.01), outperforming baseline tools. (3) The system demonstrates high scalability and cross-disciplinary transferability, offering a novel paradigm for ethically grounded, large-scale deployment of AI in education.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Learning to learn is becoming a science, driven by the convergence of knowledge tracing, signal processing, and generative AI to model student learning states and optimize education. We propose CoTutor, an AI-driven model that enhances Bayesian Knowledge Tracing with signal processing techniques to improve student progress modeling and deliver adaptive feedback and strategies. Deployed as an AI copilot, CoTutor combines generative AI with adaptive learning technology. In university trials, it has demonstrated measurable improvements in learning outcomes while outperforming conventional educational tools. Our results highlight its potential for AI-driven personalization, scalability, and future opportunities for advancing privacy and ethical considerations in educational technology. Inspired by Richard Hamming's vision of computer-aided 'learning to learn,' CoTutor applies convex optimization and signal processing to automate and scale up learning analytics, while reserving pedagogical judgment for humans, ensuring AI facilitates the process of knowledge tracing while enabling learners to uncover new insights.

Problem

• Enhancing student progress modeling through AI
• Delivering adaptive feedback and learning strategies
• Automating learning analytics while preserving human pedagogy

Innovation

• Enhances Bayesian Knowledge Tracing with signal processing
• Combines generative AI with adaptive learning technology
• Applies convex optimization to automate learning analytics