NotebookLM: An LLM with RAG for active learning and collaborative tutoring

This study explores NotebookLM, a Google Gemini powered AI platform that integrates Retrieval Augmented Generation (RAG), as a collaborative physics tutor, an area of research that is developing quickly. In our implementation, NotebookLM was configured as an AI physics collaborative tutor to support students in solving conceptually oriented physics problems using a collaborative, Socratic approach. When deployed as a collaborative tutor, the system restricts student interaction to a chat only interface, promoting controlled and guided engagement. By grounding its responses in teacher provided source documents, NotebookLM helps mitigate one of the major shortcomings of standard large language models--hallucinations--thereby ensuring more traceable and reliable answers. Our experiments demonstrate NotebookLM's potential as a low cost, easily implemented RAG based tool for personalized and traceable AI assisted physics learning in diverse educational settings. Furthermore, NotebookLM also functions as a valuable study tool for both teachers and students by generating targeted questions, study guides, and supplementary materials that enhance both classroom instruction and independent research. While limitations remain, particularly regarding legal restrictions, the current text only mode of interaction, and the intrinsic reliability challenges of statistical models, this work presents a promising example of a grounded AI application in physics education.