ACE : automated technical debt remediation with validated large language model refactorings
(2025) p.1318-1324- Abstract
- The remarkable advances in AI and Large Language Models (LLMs) have enabled machines to write code, accelerating the growth of software systems. However, the bottleneck in software development is not writing code but understanding it; program understanding is the dominant activity, consuming approximately 70% of developers' time. This implies that improving existing code to make it easier to understand has a high payoff and - in the age of AI-assisted coding - is an essential activity to ensure that a limited pool of developers can keep up with ever-growing codebases.
This paper introduces Augmented Code Engineering (ACE), a tool that automates code improvements using validated LLM output. Developed through a data-driven approach,... (More) - The remarkable advances in AI and Large Language Models (LLMs) have enabled machines to write code, accelerating the growth of software systems. However, the bottleneck in software development is not writing code but understanding it; program understanding is the dominant activity, consuming approximately 70% of developers' time. This implies that improving existing code to make it easier to understand has a high payoff and - in the age of AI-assisted coding - is an essential activity to ensure that a limited pool of developers can keep up with ever-growing codebases.
This paper introduces Augmented Code Engineering (ACE), a tool that automates code improvements using validated LLM output. Developed through a data-driven approach, ACE provides reliable refactoring suggestions by considering both objective code quality improvements and program correctness. Early feedback from users suggests that AI-enabled refactoring helps mitigate code-level technical debt that otherwise rarely gets acted upon. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/5b05e57f-1d71-4e04-9620-b81a8b7680ea
- author
- Tornhill, Adam
; Borg, Markus
LU
; Hagatulah, Nadim
LU
and Söderberg, Emma LU
- organization
- publishing date
- 2025-07-28
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- FSE Companion '25 : Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering - Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering
- pages
- 1318 - 1324
- publisher
- Association for Computing Machinery (ACM)
- ISBN
- 979-8-4007-1276-0
- DOI
- 10.1145/3696630.3730565
- language
- English
- LU publication?
- yes
- id
- 5b05e57f-1d71-4e04-9620-b81a8b7680ea
- date added to LUP
- 2025-08-18 13:42:17
- date last changed
- 2025-09-25 15:34:27
@inproceedings{5b05e57f-1d71-4e04-9620-b81a8b7680ea, abstract = {{The remarkable advances in AI and Large Language Models (LLMs) have enabled machines to write code, accelerating the growth of software systems. However, the bottleneck in software development is not writing code but understanding it; program understanding is the dominant activity, consuming approximately 70% of developers' time. This implies that improving existing code to make it easier to understand has a high payoff and - in the age of AI-assisted coding - is an essential activity to ensure that a limited pool of developers can keep up with ever-growing codebases.<br/><br/>This paper introduces Augmented Code Engineering (ACE), a tool that automates code improvements using validated LLM output. Developed through a data-driven approach, ACE provides reliable refactoring suggestions by considering both objective code quality improvements and program correctness. Early feedback from users suggests that AI-enabled refactoring helps mitigate code-level technical debt that otherwise rarely gets acted upon.}}, author = {{Tornhill, Adam and Borg, Markus and Hagatulah, Nadim and Söderberg, Emma}}, booktitle = {{FSE Companion '25 : Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering}}, isbn = {{979-8-4007-1276-0}}, language = {{eng}}, month = {{07}}, pages = {{1318--1324}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{ACE : automated technical debt remediation with validated large language model refactorings}}, url = {{http://dx.doi.org/10.1145/3696630.3730565}}, doi = {{10.1145/3696630.3730565}}, year = {{2025}}, }