NaviEdu: Dual-Path Knowledge Tracing for Detecting Knowledge Shifts and Driving Targeted Interventions

Abstract

AI-driven education systems seek to infer latent knowledge states and deliver adaptive feedback, enabling personalized learning at scale. Existing approaches span generation- and interaction-based methods as well as feedback-focused systems, but they are largely designed as loosely coupled pipelines. As a result, these methods often lack fine-grained modeling of evolving knowledge states and fail to detect sudden shifts, making it difficult to translate signals into effective personalized interventions. To overcome these issues, we propose NaviEdu, a dual-path causal inference framework where a neural module captures non-linear dynamics and a graph module encodes structured reasoning. he two pathways are coordinated via consistency alignment, Laplacian regularization, and gradient-sensitive updates to keep coherent knowledge representations. A dynamic knowledge graph with feedback further enables a diagnose-intervene-re-diagnose cycle for personalized adaptation. Experiments on three benchmark datasets demonstrate that NaviEdu consistently achieves state-of-the-art AUC and accuracy, with up to 2.2% improvements over strong baselines, while maintaining competitive RMSE and r2