From Overload to Insight: Bridging Code Search and Code Review with LLMs

The software engineering (SE) research community has developed numerous tools to search and extract actionable insights from software artifacts, ranging from static analysis tools to testing frameworks and continuous integration pipelines (hereafter just "search tools"). Despite their potential, many of these search tools remain underutilized during code review, a critical process for ensuring software quality. Key challenges include the overwhelming volume of information generated by automated tools, high false-positive rates, and the need for manual configuration or interpretation, which disrupts the flow of review. In this paper, we propose a vision for an LLM-powered conversational agent designed to assist code reviewers by bridging the gap between human reviewers and search tools. This agent would summarize relevant insights, tailor them to the specific code change under review, and facilitate context-aware interactions. By enhancing the human-in-the-loop nature of code review, such a tool has the potential to amplify reviewer effectiveness, streamline the review process, and ultimately improve software quality.