Saltar al contenido
República del Perú · Observatorio de la producción científica universitaria
OApol.org Observatorio de Inteligencia Científica Universitaria del Perú
OApol.org
Inicio Universidades Publicaciones Investigadores
Repositorios
Tesis y trabajos académicosRevistas
Indicadores
Ranking trimestralRanking por carreraObjetivos de Desarrollo SostenibleReporte OCDERed neuronal 3D
Acerca
MetodologíaPrivacidad

Impact of generative artificial intelligence-based virtual tutors on self-directed mathematics learning: a systematic review

Portilla Peralta C.G. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2026) · DOI: 10.18687/laccei2026.1.1.2252

Resumen

The emergence of Generative Artificial Intelligence (GenAI) and Large Language Models (LLMs) reconfigures mathematics education, shifting the boundaries of traditional instruction toward dynamic conversational tutoring models. Objective: This study analyzes the impact of GenAI-based virtual tutors on self-directed learning in mathematics, identifying pedagogical trends, benefits for autonomy, and implementation challenges. Methodology: The authors conducted a systematic literature review of studies published between 2022 and 2026, following PRISMA guidelines. They restricted the search to Spanish-language publications to specifically analyze the technological impact within the Ibero-American and Spanish-speaking educational context. Furthermore, they evaluated the methodological rigor of the selected studies using standard tools (CASP and statistical criteria). Results: The highest-quality methodological studies indicate that GenAI integration significantly improves academic performance and the understanding of abstract concepts (such as functions and calculus), while reducing math anxiety and cognitive load. These tools act as scaffolding that fosters self-regulation through immediate and personalized feedback. However, researchers identified critical risks associated with data accuracy ("hallucinations") and a potential technological dependence that limits critical thinking. Conclusions: Virtual tutors are effective catalysts for the personalization of mathematical learning, provided their implementation is mediated by critical digital literacy strategies and instructional design that prioritizes human validation. Finally, due to the language restriction, these findings reflect the specific realities of the Spanish-speaking educational culture and are not directly generalizable worldwide.

Instituciones: Universidad Nacional de San Agustín de Arequipa