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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rinja, Daiana, Oliveira, Eduardo Araujo, López-Pernas, Sonsoles, Saqr, Mohammed, Specht, Marcus, Misiejuk, Kamila
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911633528324096
author Rinja, Daiana
Oliveira, Eduardo Araujo
López-Pernas, Sonsoles
Saqr, Mohammed
Specht, Marcus
Misiejuk, Kamila
author_facet Rinja, Daiana
Oliveira, Eduardo Araujo
López-Pernas, Sonsoles
Saqr, Mohammed
Specht, Marcus
Misiejuk, Kamila
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27134
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unpacking Vibe Coding: Help-Seeking Processes in Student-AI Interactions While Programming
Rinja, Daiana
Oliveira, Eduardo Araujo
López-Pernas, Sonsoles
Saqr, Mohammed
Specht, Marcus
Misiejuk, Kamila
Artificial Intelligence
Human-Computer Interaction
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.
title Unpacking Vibe Coding: Help-Seeking Processes in Student-AI Interactions While Programming
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2604.27134