Amplifiers or Equalizers? A Longitudinal Study of LLM Evolution in Software Engineering Project-Based Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917111567220736 |
|---|---|
| author | Kataoka, Hana Li, Jialong Matsuno, Yutaka |
| author_facet | Kataoka, Hana Li, Jialong Matsuno, Yutaka |
| contents | As LLMs reshape software development, integrating LLM-augmented practices into SE education has become imperative. While existing studies explore LLMs' educational use in introductory programming or isolated SE tasks, their impact in more open-ended Project-Based Learning (PBL) remains unexplored. This paper introduces a two-year longitudinal study comparing a 2024 (using early free LLMs, $n$=48) and 2025 (using the latest paid LLMs, $n$=46) cohort. Our findings suggest the latest powerful LLMs' dual role: they act as "equalizers," boosting average performance even for programming-weak students, providing opportunities for more authentic SE practices; yet also as "amplifiers," dramatically widening absolute performance gaps, creating new pedagogical challenges for addressing educational inequities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_23157 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Amplifiers or Equalizers? A Longitudinal Study of LLM Evolution in Software Engineering Project-Based Learning Kataoka, Hana Li, Jialong Matsuno, Yutaka Software Engineering Human-Computer Interaction As LLMs reshape software development, integrating LLM-augmented practices into SE education has become imperative. While existing studies explore LLMs' educational use in introductory programming or isolated SE tasks, their impact in more open-ended Project-Based Learning (PBL) remains unexplored. This paper introduces a two-year longitudinal study comparing a 2024 (using early free LLMs, $n$=48) and 2025 (using the latest paid LLMs, $n$=46) cohort. Our findings suggest the latest powerful LLMs' dual role: they act as "equalizers," boosting average performance even for programming-weak students, providing opportunities for more authentic SE practices; yet also as "amplifiers," dramatically widening absolute performance gaps, creating new pedagogical challenges for addressing educational inequities. |
| title | Amplifiers or Equalizers? A Longitudinal Study of LLM Evolution in Software Engineering Project-Based Learning |
| topic | Software Engineering Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.23157 |