SYSTEMATIC REVIEW article
Front. Educ.
Sec. Digital Learning Innovations
This article is part of the Research TopicArtificial Intelligence in Educational Technology: Innovations, Impacts, and Future DirectionsView all 20 articles
Intelligent Learning Systems in Primary and Secondary Education: A Systematic Review (2014-2024)
Provisionally accepted
- University of Santiago de Cali, Cali, Colombia
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
ABSTRACT Intelligent Learning Systems (ILS) are AI-enhanced educational technologies increasingly implemented in primary and secondary education with significant global variation. This systematic review synthesizes evidence on ILS effectiveness and implementation following PRISMA 2020 guidelines. We analyzed 72 peer-reviewed articles from Scopus and Web of Science (2014-2024) using systematic evidence synthesis and thematic analysis. Results demonstrate 89% overall positive outcomes across diverse educational contexts, with variation by discipline: mathematics (92%, n=25), sciences (88%, n=8), and language learning (100%, n=4). Intelligent Tutoring Systems dominate implementations (46%), followed by programming tools (19%) and gamification platforms (11%). Regional analysis identifies distinct pedagogical approaches: European focus on personalization and self-regulation, Latin American innovation in gamification and affective dimensions, North American emphasis on equity and achievement gaps, and Asian integration of sophisticated analytics. Critical effectiveness factors include pedagogical design alignment, feedback quality, adaptive personalization, affective elements, gamification, curricular integration, teacher preparation, and equity considerations. Computational thinking development emerges as an underexplored dimension in STEM implementations. This review establishes ILS efficacy for personalized learning and immediate feedback while identifying methodological gaps requiring longitudinal research, standardized effectiveness metrics, and deeper investigation of non-STEM applications and equity implications.
Keywords: Adaptive Learning, Artificial intelligence in education, Educational Technology, Intelligent learning systems, Primary education, PRISMA, Secondary education, Systematicreview
Received: 08 Oct 2025; Accepted: 21 Jan 2026.
Copyright: © 2026 Ceron and burbano. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Edison Ceron
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.