Context-Aware Conversational Tutors for Longitudinal Learning in Engineering Education

This project aims to serve the national interest by helping engineering programs address the growing pressure to accommodate increasing enrollments while maintaining personalized instruction. Generative Artificial Intelligence (AI) tools have created new challenges: students frequently use them to obtain answers rather than develop the reasoning and problem-solving skills that define engineering competence. This Level 2 Engaged Student Learning project plans to address both challenges by developing and evaluating an AI-enhanced learning platform that pairs conversational AI tutors with immersive learning environments across four undergraduate Industrial Engineering courses at the University of Texas at Arlington, spanning freshman through senior years. Rather than providing answers, the AI tutor will guide students through structured reasoning conversations, offering personalized feedback and revision opportunities that mirror expert mentorship. The project aims to strengthen technical skills, build capacity for ethical AI engagement, and prepare students for an AI-enabled workforce. The project will partner with community colleges, engage high school students, and offer faculty training for broader adoption. The project plans to integrate Large Language Model based conversational tutors within immersive environments across five levels of Bloom's Revised Taxonomy, creating a longitudinal, multi-course AI tutoring intervention. The system will employ retrieval-augmented generation to produce course-specific and assignment-aligned responses, while a dual-phase assessment model will require students to critically revise AI-generated drafts, thereby reinforcing metacognition. A mixed-methods longitudinal evaluation will examine student performance, engagement, and responsible AI use, with both Virtual Reality (VR) and two-dimensional platforms. Expected contributions include empirical knowledge on how AI scaffolding shapes technical competence and ethical AI literacy, principles for responsible AI integration in STEM, and a freely available, scalable framework for adoption across disciplines and institutions. The NSF IUSE: EDU Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.