Code review is a crucial but often complex, subjective, and time-consuming activity in software development. Over the past decades, significant efforts have been made to automate this process. Early approaches focused on knowledge-based systems (KBS) that apply rule-based mechanisms to detect code issues, providing precise feedback but struggling with complex, context-dependent cases. More recent work has shifted toward fine-tuning pre-trained language models for code review, enabling broader issue coverage but often at the expense of precision. In this paper, we propose a hybrid approach that combines the strengths of KBS and learning-based systems (LBS) to generate high-quality, comprehensive code reviews. Our method integrates knowledge at three distinct stages of the language model pipeline: during data preparation (DataAugmented Training, DAT), at inference (Retrieval-Augmented Generation, RAG), and after inference (Naive Concatenation of Outputs, NCO). We empirically evaluate our combination strategies against standalone KBS and LBS fine-tuned on a realworld dataset. Our results show that these hybrid strategies enhance the relevance, completeness, and overall quality of review comments, effectively bridging the gap between rule-based tools and deep learning models.

In code review, generating structured and relevant comments is crucial for identifying code issues and facilitating accurate code changes that ensure an efficient code review process. Well-crafted comments not only streamline the code review itself but are also essential for subsequent tasks like code refinement, where the code is modified to satisfy the input review comment. Although various AI-based approaches aimed to automate comment generation, their effectiveness remains limited by the quality of the training data. Existing code review datasets are often noisy and unrefined, posing limitations to the learning potential of AI models and hindering the automation process. To address these challenges, we propose a curation pipeline designed to enhance the quality of the largest publicly available code review dataset. We begin by establishing an evaluation framework, incorporating specific criteria and categories to empirically study the initial quality of the dataset. Using a large language model (LLM)-driven approach, we then apply our curation pipeline to refine the dataset. A comparative analysis of the newly curated dataset, based on the same evaluation framework, demonstrates substantial improvements in the clarity and conciseness of the comments. Additionally, we assess the impact of the curated dataset on automating downstream tasks, specifically comment generation and code refinement. Our findings show that the curated dataset leads to enhanced model performance in generating more accurate comments. Curated comments are also more useful as they lead to more accurate code refinement.

In model-driven engineering, the concrete syntax of a domain-specific modeling language (DSML) is fundamental as it constitutes the primary point of interaction between the user and the DSML. Nevertheless, the conventional one-size-fits-all approach to concrete syntax often undermines the effectiveness of DSMLs, as it fails to accommodate the diverse constraints and specific requirements inherent to diverse users and usage contexts. Such shortcomings can lead to a significant decline in the performance, usability, and efficiency of DSMLs. This vision paper proposes a conceptual framework to generate concrete syntax intelligently. Our framework considers multiple concerns of users and aims to align the concrete syntax with the context of the DSML usage. Additionally, we detail a baseline process to employ our framework in practice, leveraging large language models to expedite the generation of tailored concrete syntax. We illustrate the potential of our vision with two concrete examples and discuss the shortcomings and research challenges of current intelligent generation techniques.

Modern code review is a process for early detection and reduction of issues, which assists in ensuring the quality of the source code, detecting anomalies, and identifying potential improvements. However, this is a highly manual activity that requires a lot of resources and time. Recent research has addressed these problems by attempting to entirely automate this task (i.e., generating code reviews). However, we do believe that dismissing the reviewer from this process is not the best option in terms of its optimal functioning, especially considering the high error rates in the proposed approaches. Furthermore, this full automation is still too far to achieve given the complexity of the task that requires human intelligence. In this work, we aim to assist the reviewer in the code review process. We propose an approach for detecting the type of issue and locating parts of the code that need to be revised by developers. In the first phase, we propose a meta-learner that combines a learning-based model and a knowledge-based model to predict the type of issue from the review comment. Then, we use this component to create and label a large dataset composed of quadruplets. We use this data set to finetune a pre-trained language model to predict the types of issues (e.g., naming, resource handling, etc.), that need to be addressed in the original code snippet. Furthermore, we fine-tune another pre-trained language model to locate these issues in the source code submitted by developers. We evaluate the performance of our approach using a test set not considered during the training. Our results show that our model accurately locates and predicts the types of issues.

The documentation of code changes is significantly important but developers ignore it, most of the time, due to the pressure of the deadlines. While developers may document the most important features modification or bugs fixing, recent empirical studies show that the documentation of quality improvements and/or refactoring is often omitted or not accurately described. However, the automated or semi-automated documentation of refactorings has not been yet explored despite the extensive work on the remaining steps of refactoring including the detection, prioritization and recommendation. In this paper, we propose a semi-automated refactoring documentation bot that helps developers to interactively check and validate the documentation of the refactorings and/or quality improvements at the file level for each opened pull-request before being reviewed or merged to the master. The bot starts by checking the pullrequest if there are significant quality changes and refactorings at the file level and whether they are documented by the developer. Then, it checks the validity of the developers description of the refactorings, if any. Based on that analysis, the documentation bot will recommend a message to document the refactorings, their locations and the quality improvement for that pull-request when missing information is found. Then, the developer can modify his pull request description by interacting with the bot to accept/modify/reject part of the proposed documentation. Since refactoring do not happen in isolation most of the time, the bot is documenting the impact of a sequence of refactorings, in a pull-request, on quality and not each refactoring in isolation. We conducted a human survey with 14 active developers to manually evaluate the relevance and the correctness of our tool on different pull requests of 5 open source projects and one industrial system. The results show that the participants found that our bot facilitates the documentation of their quality-related changes and refactorings.