Saved in:
Bibliographic Details
Main Authors: Lee, Unggi, Kim, Joo Young, Ju, Ran, Jung, Minyoung, Eo, Jeyeon
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914233216663552
author Lee, Unggi
Kim, Joo Young
Ju, Ran
Jung, Minyoung
Eo, Jeyeon
author_facet Lee, Unggi
Kim, Joo Young
Ju, Ran
Jung, Minyoung
Eo, Jeyeon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01708
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription
Lee, Unggi
Kim, Joo Young
Ju, Ran
Jung, Minyoung
Eo, Jeyeon
Computation and Language
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.
title A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription
topic Computation and Language
url https://arxiv.org/abs/2601.01708