Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Does co-development with ai assistants lead to more maintainable code? : A registered report

Borg, Markus LU ; Hewett, Dave ; Graha,, Donald ; Couderc, Noric LU orcid ; Söderberg, Emma LU orcid ; Church, Luke and Farley, Dave (2024) 40th International Conference on Software Maintenance and Evolution
Abstract
[Background/Context] AI assistants like GitHub Copilot are transforming software engineering; several studies have highlighted productivity improvements. However, their impact on code quality, particularly in terms of maintainability, requires further investigation.

[Objective/Aim] This study aims to examine the influence of AI assistants on software maintainability, specifically assessing how these tools affect the ability of developers to evolve code.

[Method] We will conduct a two-phased controlled experiment involving professional developers. In Phase 1, developers will add a new feature to a Java project, with or without the aid of an AI assistant. Phase 2, a randomized controlled trial, will involve a different... (More)
[Background/Context] AI assistants like GitHub Copilot are transforming software engineering; several studies have highlighted productivity improvements. However, their impact on code quality, particularly in terms of maintainability, requires further investigation.

[Objective/Aim] This study aims to examine the influence of AI assistants on software maintainability, specifically assessing how these tools affect the ability of developers to evolve code.

[Method] We will conduct a two-phased controlled experiment involving professional developers. In Phase 1, developers will add a new feature to a Java project, with or without the aid of an AI assistant. Phase 2, a randomized controlled trial, will involve a different set of developers evolving random Phase 1 projects - working without AI assistants. We will employ Bayesian analysis to evaluate differences in completion time, perceived productivity, code quality, and test coverage. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to conference
publication status
published
subject
pages
7 pages
conference name
40th International Conference on Software Maintenance and Evolution
conference location
Flagstaff, United States
conference dates
2024-10-06 - 2024-10-11
language
English
LU publication?
yes
id
8fff3e1e-4d0c-4b6f-bbfb-d25dac6ec39e
alternative location
https://arxiv.org/abs/2408.10758
date added to LUP
2025-08-18 15:56:09
date last changed
2025-09-26 13:57:32
@misc{8fff3e1e-4d0c-4b6f-bbfb-d25dac6ec39e,
  abstract     = {{[Background/Context] AI assistants like GitHub Copilot are transforming software engineering; several studies have highlighted productivity improvements. However, their impact on code quality, particularly in terms of maintainability, requires further investigation. <br/><br/>[Objective/Aim] This study aims to examine the influence of AI assistants on software maintainability, specifically assessing how these tools affect the ability of developers to evolve code. <br/><br/>[Method] We will conduct a two-phased controlled experiment involving professional developers. In Phase 1, developers will add a new feature to a Java project, with or without the aid of an AI assistant. Phase 2, a randomized controlled trial, will involve a different set of developers evolving random Phase 1 projects - working without AI assistants. We will employ Bayesian analysis to evaluate differences in completion time, perceived productivity, code quality, and test coverage.}},
  author       = {{Borg, Markus and Hewett, Dave and Graha,, Donald and Couderc, Noric and Söderberg, Emma and Church, Luke and Farley, Dave}},
  language     = {{eng}},
  month        = {{08}},
  title        = {{Does co-development with ai assistants lead to more maintainable code? : A registered report}},
  url          = {{https://arxiv.org/abs/2408.10758}},
  year         = {{2024}},
}