Automated Code Review Using Large Language Models with Symbolic Reasoning
This addresses the time-consuming and subjective nature of manual code review for software developers, though it is incremental as it builds on existing AI methods.
The study tackled the problem of automating code review by integrating symbolic reasoning with large language models to enhance logical reasoning capabilities, resulting in improved accuracy and efficiency on the CodexGlue dataset compared to models like CodeT5 and CodeBERT.
Code review is one of the key processes in the software development lifecycle and is essential to maintain code quality. However, manual code review is subjective and time consuming. Given its rule-based nature, code review is well suited for automation. In recent years, significant efforts have been made to automate this process with the help of artificial intelligence. Recent developments in Large Language Models (LLMs) have also emerged as a promising tool in this area, but these models often lack the logical reasoning capabilities needed to fully understand and evaluate code. To overcome this limitation, this study proposes a hybrid approach that integrates symbolic reasoning techniques with LLMs to automate the code review process. We tested our approach using the CodexGlue dataset, comparing several models, including CodeT5, CodeBERT, and GraphCodeBERT, to assess the effectiveness of combining symbolic reasoning and prompting techniques with LLMs. Our results show that this approach improves the accuracy and efficiency of automated code review.