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

2026-01-23

AI Summary

This work addresses the limitations of existing knowledge tracing methods, which struggle to effectively model deep relationships among knowledge concepts and suffer from high computational costs and noise sensitivity when using full-graph encoding, thereby constraining predictive performance. To overcome these challenges, we propose a multi-view heterogeneous graph framework that dynamically extracts knowledge concept relationships through a multi-agent mechanism and integrates a student–exercise interaction graph. Leveraging a student’s historical interactions, the framework conditionally retrieves high-value subgraphs and employs an asymmetric cross-attention module to efficiently fuse multi-source information. This approach substantially mitigates attention dispersion and enhances the representation of knowledge concept relationships. Experimental results on three benchmark datasets demonstrate that our method outperforms state-of-the-art approaches in both knowledge relationship modeling accuracy and next-question prediction performance.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Knowledge Tracing
• Graph-based KT
• Inter-concept Relations
• Heterogeneous Graph
• Attention Diffusion

Innovation

• Multi-Agent Graph
• Subgraph Retrieval
• Asymmetric Fusion
• Knowledge Tracing
• Heterogeneous Graph