Intelligent Personalized Learning Guide Using Generative AI

The evolution of education from static, one-size-fits-all systems to adaptive, data-driven paradigms marks a profound shift in how knowledge is delivered and consumed. Traditional pedagogical models fail to accommodate individual differences in learning pace, style, and cognitive ability. This paper presents an Intelligent Personalised Learning Guide (IPLG) that leverages Generative Artificial Intelligence (AI) to create customized learning experiences. By combining Large Language Models (LLMs) with dynamic learner profiling, the system generates context-aware study materials, adaptive quizzes, and intelligent feedback mechanisms. The proposed framework not only bridges the gap between learners and educational resources but also enhances comprehension and engagement by continuously adapting to learner performance and behavioral data.The proposed system integrates a Generative AI Engine, a Data Collection and Profiling Layer, and an Adaptive Content Generation Module to deliver interactive, feedback-rich, and personalized learning paths. The use of Generative AI ensures that each learner receives unique content aligned with their current knowledge level, while performance analytics provide actionable insights for continuous improvement. Experiments and literature synthesis suggest that such agentic systems have the potential to revolutionize digital learning environments by transforming static educational resources into intelligent, self-evolving learning companions. This research contributes to the growing field of AI in Education (AIED) by proposing an adaptive framework that enhances personalization, scalability, and learner autonomy.