Automated Code Review Using Large Language Models at Ericsson: An Experience Report
This addresses the problem of time constraints for experienced developers in software quality assurance at Ericsson, but it is incremental as it builds on existing LLM and static analysis methods.
The paper tackles automating code review to reduce cognitive burden on developers by using Large Language Models and static program analysis at Ericsson, reporting encouraging preliminary results from experiments with experienced developers.
Code review is one of the primary means of assuring the quality of released software along with testing and static analysis. However, code review requires experienced developers who may not always have the time to perform an in-depth review of code. Thus, automating code review can help alleviate the cognitive burden on experienced software developers allowing them to focus on their primary activities of writing code to add new features and fix bugs. In this paper, we describe our experience in using Large Language Models towards automating the code review process in Ericsson. We describe the development of a lightweight tool using LLMs and static program analysis. We then describe our preliminary experiments with experienced developers in evaluating our code review tool and the encouraging results.