Project Grant 2507128

This $841,392 Project Grant was awarded by the National Science Foundation's STEM Education program (CFDA 47.076) to the University of Georgia Research Foundation, Inc. The project aims to develop and evaluate a scalable, explainable, teacher-in-the-loop adaptive learning system built on large language models. Key components include an assessment module to assist instructors in generating aligned and explainable assessment tasks, a recommendation module to create personalized learning pathways using a novel sparse autoencoder-based explanation technique, and a conversation module to facilitate real-time interaction with students and teachers. The system will be piloted with approximately 5 instructors and 950 undergraduate students in introductory physics courses. By making the software open-source and accessible to instructors nationwide, the project will promote the progress of science and support broader educational access, while advancing AI literacy among educators and laying the foundation for human-centered AI systems in education.