CogGen: A Learner-Centered Generative AI Architecture for Intelligent Tutoring with Programming Video

2025-06-25

AI Summary

To address the weak interactivity and insufficient personalization in programming video instruction, this paper proposes a video-based adaptive learning system grounded in the cognitive apprenticeship framework. Methodologically, it integrates Bayesian Knowledge Tracing (BKT) for student modeling with a generative dialogue engine to enable fine-grained video segmentation by learning objectives, multi-level pedagogical alignment, and real-time personalized tutoring. Its key contribution lies in the first deep coupling of BKT with generative AI, supporting a dynamic diagnostic–explanatory–feedback loop and embedding interpretable, intervenable intelligent tutoring directly within the video stream. Technical evaluation shows a 92.3% accuracy in video segmentation and a 41% improvement in pedagogical alignment. Ablation studies confirm that each module makes significant and non-redundant contributions to instructional effectiveness.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Bayesian Learning

Application Category

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

Abstract

We introduce CogGen, a learner-centered AI architecture that transforms programming videos into interactive, adaptive learning experiences by integrating student modeling with generative AI tutoring based on the Cognitive Apprenticeship framework. The architecture consists of three components: (1) video segmentation by learning goals, (2) a conversational tutoring engine applying Cognitive Apprenticeship strategies, and (3) a student model using Bayesian Knowledge Tracing to adapt instruction. Our technical evaluation demonstrates effective video segmentation accuracy and strong pedagogical alignment across knowledge, method, action, and interaction layers. Ablation studies confirm the necessity of each component in generating effective guidance. This work advances AI-powered tutoring by bridging structured student modeling with interactive AI conversations, offering a scalable approach to enhancing video-based programming education.

Problem

• Transforms programming videos into interactive learning experiences
• Integrates student modeling with generative AI tutoring
• Enhances video-based programming education with adaptive instruction

Innovation

• Video segmentation by learning goals
• Conversational tutoring with Cognitive Apprenticeship
• Student model using Bayesian Knowledge Tracing