MAGE-KT: Multi-Agent Graph-Enhanced Knowledge Tracing with Subgraph Retrieval and Asymmetric Fusion

TL;DR

MAGE-KT introduces a multi-agent, subgraph retrieval, and asymmetric fusion approach to improve knowledge tracing by better modeling inter-concept relations and reducing noise from large graphs, leading to more accurate student performance predictions.

Contribution

It proposes a novel multi-view heterogeneous graph framework with subgraph retrieval and asymmetric fusion, enhancing knowledge tracing accuracy over existing graph-based methods.

Findings

Significant improvement in KC-relation accuracy.

Enhanced next-question prediction performance.

Effective reduction of noise from large graphs.

Abstract

Knowledge Tracing (KT) aims to model a student's learning trajectory and predict performance on the next question. A key challenge is how to better represent the relationships among students, questions, and knowledge concepts (KCs). Recently, graph-based KT paradigms have shown promise for this problem. However, existing methods have not sufficiently explored inter-concept relations, often inferred solely from interaction sequences. In addition, the scale and heterogeneity of KT graphs make full-graph encoding both computationally both costly and noise-prone, causing attention to bleed into student-irrelevant regions and degrading the fidelity of inter-KC relations. To address these issues, we propose a novel framework: Multi-Agent Graph-Enhanced Knowledge Tracing (MAGE-KT). It constructs a multi-view heterogeneous graph by combining a multi-agent KC relation extractor and a student-question interaction graph, capturing complementary semantic and behavioral signals. Conditioned on the target student's history, it retrieves compact, high-value subgraphs and integrates them using an Asymmetric Cross-attention Fusion Module to enhance prediction while avoiding attention diffusion and irrelevant computation. Experiments on three widely used KT datasets show substantial improvements in KC-relation accuracy and clear gains in next-question prediction over existing methods.