Collaborative Research: Empowering STEM Education by Creating Benchmarking Models for GenAI Learning Assistants

About This Grant

This IUSE Level 1 project aims to serve the national interest by creating generative artificial intelligence (GenAI) learning assistants tailored to architecture, engineering, and construction (AEC) education, thereby helping students develop independent problem-solving skills. AEC is a unique, cross-disciplinary field in STEM entered on complex project-based learning, requiring deep information resources and personalized learning support. By focusing on the significance of providing real-time, course-specific feedback and personalized guidance, the GenAI learning assistants will help students understand complex concepts, boost their confidence, and foster more consistent independent learning. The project also aims to better understand how GenAI adoption strategies can be tailored to different AEC courses and academic levels. The project’s insights could be adapted to other STEM disciplines where project-based learning is integral. This proposed research involves the development and evaluation of three course-specific GenAI learning assistants: one for Construction Graphics (freshmen), one for Structural Systems (juniors), and one for Human-Building Interaction (seniors). The assistants will feature automated symbol identification in construction drawings, 3D visualization of load distributions, augmented onto real-world structures, and coding and hardware configuration support for developing intelligent building sensing systems. The core hypothesis is that adopting the GenAI learning assistants will enhance student learning and promote self-regulated learning (SRL). Each GenAI learning assistant is grounded in key SRL principles such as goal setting, self-monitoring, self-reflection, and strategic help-seeking—skills essential for preparing future AEC professionals. The immediate outcomes will transform AEC education by providing empirical evidence of the effectiveness of GenAI learning assistants. In addition, these results will help educators understand how GenAI-enhanced learning supports influence AEC student perceptions and use of AI after completing those courses. 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.