Artificial intelligence in improving reading comprehension of K-12 students: A systematic literature review

Abstract

The educational use of artificial intelligence (AI) has expanded rapidly in recent years, offering new possibilities for individualized instruction and learner support. Despite its growing relevance, AI’s effectiveness in the development of reading comprehension among K-12 students remains limited. This systematic review synthesizes findings from 19 empirical studies that implemented AI-based interventions to enhance students’ reading comprehension. Following PRISMA guidelines, five major databases were searched for English-language peer-reviewed empirical studies published between 2015 and 2025 that examined AI-supported reading comprehension interventions in K–12 education. Nineteen studies met the predefined inclusion criteria and were synthesized across five analytical dimensions: the type of AI employed, the form of personalization included, the inclusion of SEN students, the presence of explicit comprehension strategy instruction, and reported affective and motivational outcomes. The findings reveal three overarching trends. First, AI-supported interventions consistently improved reading comprehension across diverse educational contexts. Second, personalization features, particularly adaptive feedback, individualized scaffolding, and dynamic text difficulty, emerged as instructional mechanisms most consistently associated with positive reading outcomes, regardless of the specific AI technology employed. Third, while recent studies increasingly incorporated large language models and AI-driven reading platforms, evidence regarding learners with special educational needs remained limited, restricting the generalizability of current findings. This review contributes to the literature by identifying personalization as the key instructional mechanism underlying successful AI-supported reading interventions and by highlighting important research gaps related to SEN learners, long-term effectiveness, and the transparent reporting of AI systems. These findings also provide practical guidance for educators seeking to implement AI-supported reading instruction in K–12 classrooms.