This systematic literature review explores the application of AI in detecting learning styles within adaptive learning systems. The study analyzes 40 articles published between 2014 and 2022, focusing on the effectiveness of AI-based methods for automatic learning style detection. The review highlights the challenges of traditional methods, such as tests and questionnaires, which are limited by student reluctance and lack of self-awareness. The study emphasizes the need for further research into AI algorithms for automatic detection in real-world educational settings. It identifies key areas requiring exploration, including adaptation experiment parameters, the role of machine learning techniques, and comparative analysis of different methodologies. The review finds that AI techniques, particularly data-driven approaches, enhance learning adaptation. The Felder–Silverman model and AI algorithms like Decision Trees and Artificial Neural Networks are shown to be effective across diverse contexts. Moodle is prevalent in dataset mining and learning experiments, indicating its importance in research. The study provides insights into the design and implementation of AI-driven educational solutions, focusing on adapting course content according to learning styles. The aim is to improve learning outcomes within educational environments. The review concludes that learning style is the most critical factor in the adaptation process. Learning styles are described as cognitive, affective, and physiological behaviors that influence how students process and remember new information. Various theoretical models and detection techniques, including static and dynamic methods, are discussed. The study underscores the importance of identifying learning styles to personalize and optimize the learning experience for individual learners.This systematic literature review explores the application of AI in detecting learning styles within adaptive learning systems. The study analyzes 40 articles published between 2014 and 2022, focusing on the effectiveness of AI-based methods for automatic learning style detection. The review highlights the challenges of traditional methods, such as tests and questionnaires, which are limited by student reluctance and lack of self-awareness. The study emphasizes the need for further research into AI algorithms for automatic detection in real-world educational settings. It identifies key areas requiring exploration, including adaptation experiment parameters, the role of machine learning techniques, and comparative analysis of different methodologies. The review finds that AI techniques, particularly data-driven approaches, enhance learning adaptation. The Felder–Silverman model and AI algorithms like Decision Trees and Artificial Neural Networks are shown to be effective across diverse contexts. Moodle is prevalent in dataset mining and learning experiments, indicating its importance in research. The study provides insights into the design and implementation of AI-driven educational solutions, focusing on adapting course content according to learning styles. The aim is to improve learning outcomes within educational environments. The review concludes that learning style is the most critical factor in the adaptation process. Learning styles are described as cognitive, affective, and physiological behaviors that influence how students process and remember new information. Various theoretical models and detection techniques, including static and dynamic methods, are discussed. The study underscores the importance of identifying learning styles to personalize and optimize the learning experience for individual learners.