Empowering Elementary Mathematics Learning: A Study on AI-Driven Cognitive Diagnosis and Intervention with the Jiuzhang AI-Tutor Platform

DOI

10.2991/978-94-6463-988-9_53How to use a DOI?

Keywords

Jiuzhang AI-Tutor; Cognitive Diagnosis; Personalized Intervention; Elementary Mathematics

Abstract

The integration of Artificial Intelligence (AI) into education presents a transformative opportunity to address long-standing challenges in personalized learning. This study investigates the efficacy of an AI-driven tutoring system in enhancing elementary mathematics education for third-grade students. A primary challenge in conventional classrooms is catering to the diverse cognitive depths and learning trajectories of individual students. This paper introduces the “Jiuzhang AI-Tutor,” an intelligent learning companion leveraging a fine-grained knowledge graph and a specialized Large Language Model (LLM). The platform’s core is a multi-layered cognitive diagnosis model that assesses student ability across four distinct levels, from foundational consolidation to innovative application. To evaluate its effectiveness, a quasi-experimental study was conducted with 88 third-grade students over eight weeks. An experimental group utilized the Jiuzhang AI-Tutor for adaptive diagnosis and intervention, while a control group adhered to traditional homework protocols. Statistical analysis of pre-test and post-test scores, complemented by formative learning data and user satisfaction surveys, reveals that students using the AI tutor demonstrated substantially greater improvement in mathematical understanding and problem-solving capabilities. Moreover, the experimental group exhibited higher learning motivation and reduced mathematics-related anxiety. This research provides robust empirical evidence that AI systems, when equipped with sophisticated cognitive diagnostic frameworks, can create more effective, engaging, and personalized learning ecosystems in elementary education.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jianping Jia
AU  - Lin He
AU  - Yanling Lin
PY  - 2026
DA  - 2026/02/15
TI  - Empowering Elementary Mathematics Learning: A Study on AI-Driven Cognitive Diagnosis and Intervention with the Jiuzhang AI-Tutor Platform
BT  - Proceedings of the 2025 5th International Conference on Education, Language and Art (ICELA 2025)
PB  - Atlantis Press
SP  - 482
EP  - 492
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-94-6463-988-9_53
DO  - 10.2991/978-94-6463-988-9_53
ID  - Jia2026
ER  -