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

2025-07-25

AI Summary

Senior developers face excessive cognitive load during code review, struggling to balance feature development with quality assurance. Method: This paper proposes a lightweight automated code review approach integrating large language models (LLMs) with static program analysis. Static analysis extracts structural features and potential defects, which guide the LLM to perform semantic-level understanding and generate context-sensitive, human-readable review comments—enabling dual verification of code structure and semantics. Contribution/Results: Compared to standalone LLM- or static-analysis-based approaches, our method significantly improves review accuracy and interpretability while reducing false positives. Preliminary industrial evaluation demonstrates that the tool effectively helps developers prioritize high-value review tasks, achieving a 78% comment adoption rate. Positive feedback from senior engineers confirms its feasibility and practical utility in real-world development workflows.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Evaluation and Analysis
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• Automating code review to reduce developer workload
• Using LLMs to enhance software quality assurance
• Integrating static analysis with AI for efficient reviews

Innovation

• Automating code review with Large Language Models
• Combining LLMs with static program analysis
• Lightweight tool for developer efficiency