A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription
This addresses the need for efficient and unified educational systems by reducing complexity and resource use in knowledge tracing, though it appears incremental as it builds on existing LLM-based approaches.
The authors tackled the problem of knowledge tracing (KT) by proposing Thinking-KT, a training-free framework that uses test-time scaling to enable small LLMs to achieve competitive performance, and it unifies prediction, feedback, and recommendation without degrading accuracy.
Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require fine-tuning and exhibit unstable or near-random performance. Moreover, prior KT systems primarily focus on prediction and rely on multi-stage pipelines for feedback and recommendation, resulting in increased system complexity and resources. To address this gap, we propose Thinking-KT, a training-free KT framework that incorporates Test-Time Scaling (TTS), enabling even small LLMs to achieve competitive KT performance. Moreover, in this framework, a small LLM can jointly perform KT prediction, personalized feedback generation, and learning recommendation in a unified output without degrading prediction accuracy. Beyond performance, we present the systematic analysis of reasoning traces in KT. Our results demonstrate that TTS is a critical yet underexplored factor in LLM-based KT, and that small LLMs can serve as unified ITS engines.