{"ID":2834358,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.01356","arxiv_id":"2512.01356","title":"LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM","abstract":"Code review is critical for ensuring software quality and maintainability. With the rapid growth in software scale and complexity, code review has become a bottleneck in the development process because of its time-consuming and knowledge-intensive nature and the shortage of experienced developers willing to review code. Several approaches have been proposed for automatically generating code reviews based on retrieval, neural machine translation, pre-trained models, or large language models (LLMs). These approaches mainly leverage historical code changes and review comments. However, a large amount of crucial information for code review, such as the context of code changes and prior review knowledge, has been overlooked. This paper proposes an LLM-based review knowledge-augmented, context-aware framework for code review generation, named LAURA. The framework integrates review exemplar retrieval, context augmentation, and systematic guidance to enhance the performance of ChatGPT-4o and DeepSeek v3 in generating code review comments. Besides, given the extensive low-quality reviews in existing datasets, we also constructed a high-quality dataset. Experimental results show that for both models, LAURA generates review comments that are either completely correct or at least helpful to developers in 42.2% and 40.4% of cases, respectively, significantly outperforming SOTA baselines. Furthermore, our ablation studies demonstrate that all components of LAURA contribute positively to improving comment quality.","short_abstract":"Code review is critical for ensuring software quality and maintainability. With the rapid growth in software scale and complexity, code review has become a bottleneck in the development process because of its time-consuming and knowledge-intensive nature and the shortage of experienced developers willing to review code...","url_abs":"https://arxiv.org/abs/2512.01356","url_pdf":"https://arxiv.org/pdf/2512.01356v2","authors":"[\"Yuxin Zhang\",\"Yuxia Zhang\",\"Zeyu Sun\",\"Yanjie Jiang\",\"Hui Liu\"]","published":"2025-12-01T07:10:23Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}