Unpacking Vibe Coding: Help-Seeking Processes in Student-AI Interactions While Programming

arXiv cs.AI / 5/1/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper studies “vibe coding” in higher-education programming, treating student–AI chat as a help-seeking process rather than simple language prompting.
By analyzing 19,418 interaction turns from 110 undergraduate students, the researchers compare how top vs. low performers interact with AI while programming.
Top performers tend to use instrumental help-seeking (asking questions and exploring), which triggers more tutor-like AI responses.
Low performers more often use executive help-seeking, effectively delegating tasks to the AI to produce ready-made solutions.
The authors conclude that today’s generative AI largely reflects students’ immediate intent (productive or passive) instead of optimizing for learning, and they call for pedagogically aligned AI design to reduce unproductive delegation and steer toward inquiry.

Abstract

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.