Saved in:
Bibliographic Details
Main Authors: Yu, Chi, Yuan, Hongyu, Duan, Zhiyi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915750586875904
author Yu, Chi
Yuan, Hongyu
Duan, Zhiyi
author_facet Yu, Chi
Yuan, Hongyu
Duan, Zhiyi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16886
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MAGE-KT: Multi-Agent Graph-Enhanced Knowledge Tracing with Subgraph Retrieval and Asymmetric Fusion
Yu, Chi
Yuan, Hongyu
Duan, Zhiyi
Artificial Intelligence
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.
title MAGE-KT: Multi-Agent Graph-Enhanced Knowledge Tracing with Subgraph Retrieval and Asymmetric Fusion
topic Artificial Intelligence
url https://arxiv.org/abs/2601.16886