Date
AI Overview
Why it matters
Undergraduate degree curricula often have long course sequences where a single course failure can delay graduation. Manual curriculum revision by faculty is lengthy and labor-intensive, making changes infrequent and slow to address student needs.
Study at a glance
- Question: Can large language models accurately analyze curricular complexity and suggest revisions to reduce bottlenecks and graduation delays?
- Setting and data: Undergraduate B.S. in Software Engineering degree program flow charts and course descriptions; feedback from two senior department faculty members.
- Method: Model evaluation comparing five LLMs and one RAG system, followed by faculty validation survey.
- AI tools: GPT 5.3, Sonnet 4.6, Gemini 3.1 Flash Lite Preview, Nova 2 Lite, Claude Opus 4.1
Key findings
- Claude Sonnet 4.6 was the only tested model that correctly calculated curricular complexity factors, while also providing interactive visualization tools and 83% reasonable revision suggestions.
- Although GPT 5.3, Claude Opus 4.1, and Gemini 3.1 Flash Lite correctly described complexity concepts, they all failed to calculate blocking and delay factors correctly.
- Faculty feedback indicated that while model recommendations offered useful starting points, several suggestions carried unintended consequences such as credit overload or conflicts with graduate cross-listing and existing offerings.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
The rise of Artificial Intelligence (AI) enables automatic analysis of large amounts of data. Previously time-consuming and labor-intensive tasks can be completed much more efficiently with the use of AI. This work uses AI techniques to analyze and revise curricular patterns in an undergraduate degree for Software Engineering. Curricula often have long sequences where failure to pass a class within the sequence may jeopardize completion of the degree within four years. Manual analysis and revision of curricula by university faculty is a lengthy and labor-intensive process, causing changes to occur rarely and making it impossible to keep up with the changing needs of students. This work reduces the time-to-change for curricula and reduces bottlenecks and graduation delays by using Large Language Models (LLMs) to analyze curricular patterns and suggest revisions.
Research Categories
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
Methods
AI tools
Publication Source
Publisher
arXiv
