Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing

TL;DR

This paper introduces BAIM, a novel knowledge tracing framework that models learners' problem-solving procedures dynamically, significantly improving prediction accuracy by capturing procedural stages and learner heterogeneity.

Contribution

BAIM integrates dynamic procedural solution representations into knowledge tracing, leveraging a reasoning language model and context-conditioned routing to enhance learner performance prediction.

Findings

BAIM outperforms strong baselines on XES3G5M and NIPS34 datasets.

It achieves larger gains with repeated learner interactions.

Stage-level representations capture latent procedural signals.

Abstract

Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics of problem solving. We propose Behavior-Aware Item Modeling (BAIM), a framework that enriches item representations by integrating dynamic procedural solution information. BAIM leverages a reasoning language model to decompose each item's solution into four problem-solving stages (i.e., understand, plan, carry out, and look back), pedagogically grounded in Polya's framework. Specifically, it derives stage-level representations from per-stage embedding trajectories, capturing latent signals beyond surface features. To reflect learner heterogeneity, BAIM adaptively routes these stage-wise representations, introducing a context-conditioned mechanism within a KT backbone, allowing different procedural stages to be emphasized for different learners. Experiments on XES3G5M and NIPS34 show that BAIM consistently outperforms strong pretraining-based baselines, achieving particularly large gains under repeated learner interactions.