Multi-Tier Mentorship with AI-Assisted Development: Authentic Engineering for K-12 and Undergraduates

This research introduces a novel multi-tiered mentorship framework designed to bridge the gap between K-12 students' innovative engineering ideas and their technical execution, leveraging AI-assisted development. Undergraduates provide architectural oversight, mentoring high school students who utilize large language models and AI agents for authentic engineering projects. The framework was successfully tested with LuckyTag, a privacy-preserving NFC-based lost-and-found system, demonstrating a structured approach to effective K-12 and university collaborations using emerging AI technologies.

Why it matters

This framework offers a strategic model for cultivating future talent by providing practical engineering experience to younger students and leadership opportunities for undergraduates, enhanced by cutting-edge AI tools. It addresses a critical gap in STEM education by transforming how technical skills are developed and knowledge is transferred, fostering innovation and inter-generational collaboration.

Key insights

• K-12 students often lack the technical skills to implement their creative engineering ideas.
• Undergraduate students possess coding expertise but have limited opportunities for leadership in real-world projects and mentorship.
• AI-assisted tools, including large language models and AI agents, offer a potential solution to bridge the technical skill gap.
• A multi-tiered mentorship framework can enable high school students to engage in authentic engineering while undergraduates provide architectural guidance.
• The framework facilitates effective K-12 and university collaborations in engineering.
• The LuckyTag project demonstrated the practical application and efficacy of this multi-tiered, AI-assisted mentorship model.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2608.19379