Signal Curriculum as Code: AI-Assisted Instructional Design Architecture for STEM Education

Summary

This arXiv preprint proposes a six-phase, AI-assisted instructional design architecture built around a 'Curriculum as Code' paradigm. The architecture integrates generative AI with LaTeX and Python to automate the creation of reproducible, visually consistent and technically precise materials for STEM education. The authors motivate the work by noting that creating customized instructional materials for active learning imposes a heavy workload on faculty. They also note that standard presentation tools lack robust support for technical content, while current AI tools have their own limitations for this use case. The paper was posted to arXiv's cs.CY category on 2026-08-07.