Study for Interactive Learning Pathway Generator

Personalized studying has been increasingly popular. Its research significance is to customize the personal study process, which can increase learning efficiency as well as make learning more effective. This study develops an Interactive Learning Pathway Generator which aims to make knowledge information retrieval personal and accurate and ultimately improve learning efficiency. Retrieval-augmented generation (RAG) was used to facilitate a personalized educational experience. The system is capable of automatically adjusting the course schedule based on the user's performance, as well as allowing users to adjust it themselves. The efficacy of this system was substantiated by the outcome of the experiment. The findings reveal that user engagement and learning efficiency have been greatly improved. These results showed that the potential of integrating large language models into retrieval mechanisms is evident in improving personalized education. While the system is proven efficient, its reliance on short-term performance data and manual adjustments limits scalability. Future research can integrate multiple modes of analytics and also reinforcement learning to enhance autonomous adaptability across diverse educational situations.