Date
Publisher
arXiv
Generative AI is reshaping higher education programming through vibe coding, where students collaborate with AI via natural language rather than writing code line-by-line. We conceptualize this practice as help-seeking, analyzing 19,418 interaction turns from 110 undergraduate students. Using inductive coding and Heterogeneous Transition Network Analysis, we examined interaction sequences to compare top- and low-performing students. Results reveal that top performers engaged in instrumental help-seeking -- inquiry and exploration -- eliciting tutor-like AI responses. In contrast, low performers relied on executive help-seeking, frequently delegating tasks and prompting the AI to assume an executor role focused on ready-made solutions. These findings indicate that currently generative AI mirrors student intent (whether productive or passive) rather than optimizing for learning. To evolve from tools to teammates, AI systems must move beyond passive compliance. We argue for pedagogically aligned design that detect unproductive delegation and adaptively steer educational interactions toward inquiry, ensuring student-AI partnerships augment rather than replace cognitive effort.
Study at a glance
- Question: How do student-AI interaction patterns during programming differ by performance and relate to course grades?
- Setting and data: Undergraduate artificial intelligence course at University of Massachusetts Amherst, Spring 2025, 110 students across 19,418 chat turns.
- Method: Content coding, transition network analysis (Heterogeneous Transition Network Analysis), and linear regression.
Why it matters
Students increasingly rely on conversational AI assistants for programming, but over-reliance may short-circuit essential learning processes. Evidence is needed on how student-AI dialogues unfold sequentially and whether interaction patterns relate to academic performance.
Key findings
- Top-performing students engaged in exploratory inquiry that elicited tutoring from AI, whereas low performers more often delegated tasks and received ready-made solutions.
- Receiving conceptual explanations from AI positively predicted course grades, while frequently pasting assignment text directly into prompts negatively predicted performance.
- Higher proportions of direct solution loops occurred among lower-performing students, who frequently transitioned from AI feedback or tutoring back to delegating tasks.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
