Support, not automation : towards AI-supported code review for code quality and beyond
(2025) 33rd ACM International Conference on the Foundations of SoftwareEngineering
- Abstract
- Code review is a well-established and valuable software development practice associated with code quality, interpersonal, and team benefits. However, it is also time-consuming, with developers spending 10–20% of their working time doing code reviews. With recent advances in AI capabilities, there are more and more initiatives aimed at fully automating code reviews to save time and streamline software developer workflows.
However, while automated tools might succeed in maintaining the code quality, we risk losing interpersonal and team benefits such as knowledge transfer, shared code ownership, and team awareness. Instead of automating code review and losing these important benefits, we envision a code review platform where AI is... (More) - Code review is a well-established and valuable software development practice associated with code quality, interpersonal, and team benefits. However, it is also time-consuming, with developers spending 10–20% of their working time doing code reviews. With recent advances in AI capabilities, there are more and more initiatives aimed at fully automating code reviews to save time and streamline software developer workflows.
However, while automated tools might succeed in maintaining the code quality, we risk losing interpersonal and team benefits such as knowledge transfer, shared code ownership, and team awareness. Instead of automating code review and losing these important benefits, we envision a code review platform where AI is used to support code review to increase benefits for both code quality and the development team.
We propose an AI agent-based architecture that collects and combines information to support the user throughout the code review and adapt the workflow to their needs. We analyze this design in relation to the benefits of code review and outline a research agenda aimed at realizing the proposed design. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/c071364a-5617-4954-9b1c-84b11feb9d85
- author
- Heander, Lo
LU
; Söderberg, Emma LU
and Rydenfält, Christofer LU
- organization
- publishing date
- 2025-04-26
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- in press
- subject
- keywords
- Code review, Code review tools, Agentic systems, Human-in-the-loop, Multi-agent systems, Large language models
- host publication
- 33rd ACM International Conference on the Foundations of Software Engineering : FSE Companion ’25 - FSE Companion ’25
- pages
- 5 pages
- publisher
- Association for Computing Machinery (ACM)
- conference name
- 33rd ACM International Conference on the Foundations of Software<br/>Engineering
- conference location
- Trondheim, Norway
- conference dates
- 2025-06-23 - 2025-06-28
- ISBN
- 979-8-4007-1276-0
- project
- DAPPER: Seamless, Tailored Code Review
- How can code reviews be made fit-for-purpose?
- language
- English
- LU publication?
- yes
- id
- c071364a-5617-4954-9b1c-84b11feb9d85
- date added to LUP
- 2025-05-04 12:27:01
- date last changed
- 2025-05-06 15:15:40
@inproceedings{c071364a-5617-4954-9b1c-84b11feb9d85, abstract = {{Code review is a well-established and valuable software development practice associated with code quality, interpersonal, and team benefits. However, it is also time-consuming, with developers spending 10–20% of their working time doing code reviews. With recent advances in AI capabilities, there are more and more initiatives aimed at fully automating code reviews to save time and streamline software developer workflows.<br/><br/>However, while automated tools might succeed in maintaining the code quality, we risk losing interpersonal and team benefits such as knowledge transfer, shared code ownership, and team awareness. Instead of automating code review and losing these important benefits, we envision a code review platform where AI is used to support code review to increase benefits for both code quality and the development team.<br/><br/>We propose an AI agent-based architecture that collects and combines information to support the user throughout the code review and adapt the workflow to their needs. We analyze this design in relation to the benefits of code review and outline a research agenda aimed at realizing the proposed design.}}, author = {{Heander, Lo and Söderberg, Emma and Rydenfält, Christofer}}, booktitle = {{33rd ACM International Conference on the Foundations of Software Engineering : FSE Companion ’25}}, isbn = {{979-8-4007-1276-0}}, keywords = {{Code review; Code review tools; Agentic systems; Human-in-the-loop; Multi-agent systems; Large language models}}, language = {{eng}}, month = {{04}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{Support, not automation : towards AI-supported code review for code quality and beyond}}, url = {{https://lup.lub.lu.se/search/files/218417299/Paper_Towards_a_new_Code_Review_Experience_2_.pdf}}, year = {{2025}}, }