Can Generative Artificial Intelligence Effectively Enhance Students’ Mathematics Learning Outcomes?—A Meta-Analysis of Empirical Studies from 2023 to 2025
Baoxin Liu, Wenlan Zhang, Fangfang Wang
Source record
Source: Crossref
Published: Jan 16, 2026
DOI: 10.3390/educsci16010140
Open original source ↗Source abstract
Generative artificial intelligence (GenAI) shows transformative potential in mathematics education. However, empirical findings remain inconsistent, and a systematic synthesis of its effects across distinct engagement dimensions is lacking. This preregistered meta-analysis (INPLASY2025110051) systematically reviewed 22 empirical studies (46 independent samples, N = 5232) published between 2023 and 2025. The results indicated that GenAI has a moderate positive impact on students’ mathematics learning outcomes (g = 0.534). Moderation analysis further revealed that the level of GenAI integration in teaching, sample size, and learning content are the primary factors influencing this effect. The study found that the effect was most pronounced under the creative transformation (CT) integration mode, was significant when applied to geometry learning, and was stronger in studies with small samples or small class sizes; collaborative learning approaches also significantly enhance these mathematics learning outcomes. By contrast, educational stage and intervention duration did not show significant moderating effects. The GRADE assessment indicated that while the overall evidence is supportive, the certainty of evidence is stronger for cognitive outcomes than for non-cognitive domains. The findings also offer a reference for future research on constructing a human–machine collaborative learning environment.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.