Automated Code Review Using Large Language Models at Ericsson: An Experience Report

TL;DR

This paper reports on Ericsson's experience with using Large Language Models to automate code review, aiming to reduce developer workload and improve review efficiency through a lightweight tool and static analysis.

Contribution

It presents a novel approach combining LLMs and static analysis for automated code review and shares preliminary experimental results with experienced developers.

Findings

Encouraging preliminary evaluation results

Effective integration of LLMs and static analysis

Potential to reduce developer review workload

Abstract

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.