<![CDATA[The static nature of conventional Virtual Learning Environments (VLEs) often fails to address the diverse needs of individual learners, limiting the potential for personalized education. The integration of Artificial Intelligence (AI) offers promising solutions through adaptive learning pathways. This systematic literature review aims to synthesize current evidence on AI-driven adaptive pathways in VLEs by examining: (1) types of AI algorithms used, (2) adaptation mechanisms employed, (3) impacts on learning outcomes and engagement, and (4) emerging trends and innovations. Following the PRISMA guidelines, a comprehensive search was conducted across five major databases (Scopus, Web of Science, IEEE Xplore, ACM Digital Library, and Google Scholar) for publications between 2015 and 2024. From 2,150 initially identified records, 78 studies met the inclusion criteria after rigorous screening and quality assessment using the JBI critical appraisal tools. Findings indicate that deep learning, neural networks, and natural language processing are the most commonly used AI techniques for detecting learning styles and dynamically recommending content. AI-based adaptive systems consistently improve academic performance, motivation, and engagement by up to 25% compared to traditional static VLEs. However, significant challenges related to data privacy, algorithmic bias, and infrastructural readiness persist. AI-driven adaptive pathways hold transformative potential for creating more personalized and effective digital learning experiences. Successful implementation requires addressing ethical and technical barriers through multidisciplinary collaboration and the development of inclusive, sustainable frameworks.]]>
Copyrights © 2025
