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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ramesh, Shweta, Bose, Joy, Singh, Hamender, Raghavan, A K, Roychowdhury, Sujoy, Sridhara, Giriprasad, Saini, Nishrith, Britto, Ricardo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918108336226304
author Ramesh, Shweta
Bose, Joy
Singh, Hamender
Raghavan, A K
Roychowdhury, Sujoy
Sridhara, Giriprasad
Saini, Nishrith
Britto, Ricardo
author_facet Ramesh, Shweta
Bose, Joy
Singh, Hamender
Raghavan, A K
Roychowdhury, Sujoy
Sridhara, Giriprasad
Saini, Nishrith
Britto, Ricardo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19115
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automated Code Review Using Large Language Models at Ericsson: An Experience Report
Ramesh, Shweta
Bose, Joy
Singh, Hamender
Raghavan, A K
Roychowdhury, Sujoy
Sridhara, Giriprasad
Saini, Nishrith
Britto, Ricardo
Software Engineering
Artificial Intelligence
D.2.7
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.
title Automated Code Review Using Large Language Models at Ericsson: An Experience Report
topic Software Engineering
Artificial Intelligence
D.2.7
url https://arxiv.org/abs/2507.19115