Student-focused adaptive guidance engine for intelligent tutoring with regulated learning

Abstract

Public Large Language Models (LLMs) are being increasingly explored for aiding students to learn difficult concepts. However, these LLMs do not provide course-regulated answers that are important in a tutoring context. In this paper, we present ”SAGE” (Studentfocused Adaptive Guidance Engine) as part of an intelligent tutoring framework that can enforce instructor-regulated learning through goal-oriented and learning state-based content access controls to ensure scaffolded, curricular sequencing and step-by-step guidance of students. SAGE access control features a three-layer gatekeeper mechanism that combines role-based, attribute-based, and cognitive state–based controls built on top of a knowledge graph of learner state and related course content. Evaluation results in a programming course scenario demonstrate that while promptbased baselines achieve comparable levels of helpfulness, SAGE provides significantly higher reliability in enforcing curriculum access controls. vii