Oussama Ben Sghaier

Code review is a standard practice in modern software development, aiming to improve code quality.As providing constructive reviews on a submitted patch is a challenging and error-prone task, the advances of Large Language Models (LLMs) in performing natural language processing (NLP) tasks in a human-like fashion have prompted researchers to evaluate the LLMs’ ability to automate the code review process. However, outside lab settings, it is still unclear how prone reviewers are to accept comments generated by LLMs in a real development workflow. To fill this gap, we conduct a large-scale empirical case study in a live setup to evaluate the acceptance of LLM-generated comments and their impact on the review process. This case study was performed in two organizations, Mozilla (which has its codebase available as open-source) and Ubisoft (fully closedsource). Inside their usual review environment, participants were given access to RevMate, an LLM-based assistive tool that suggests generated review comments using an off-the-shelf LLM with Retrieval-Augmented Generation to provide extra code and review context, combined with LLM-as-a-Judge, to autoevaluate the generated comments and discard irrelevant cases. Based on more than 587 patch reviews, we observed that 8.1%, of LLM-generated comments were accepted by reviewers in each organization respectively, while 14.6% and 20.5% other comments were still marked as valuable as review or development tips. Refactoring-related comments are more likely to be accepted than Functional comments (18.2% and 18.6% compared to 4.8% and 5.2%). The extra time spent by reviewers to inspect generated comments or edit accepted ones (36/119), yielding an overall median of 43s per patch, is reasonable. The accepted generated comments are as likely to yield future revisions of the revised patch as human-written comments (74% vs 73% at chunk-level).

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available signals to maximize success, alignment, whether through fine-tuning or prompting, may restrict their use. This conflict is especially salient in agentic AI settings, for instance when an agent has access to unit tests that, although intended for validation, act as strong contextual signals that can be leveraged regardless of explicit prohibitions. In this paper, we investigate how LLMs adapt their code generation strategies when exposed to test cases under different prompting conditions. Using the BigCodeBench (Hard) dataset, we design five prompting conditions that manipulate test visibility and impose explicit or implicit restrictions on their use. We evaluate five LLMs (four open-source and one closed-source) across correctness, code similarity, program size, and code churn, and analyze cross-model consistency to identify recurring adaptation strategies. Our results show that test visibility dramatically alters performance, correctness nearly doubles for some models, while explicit restrictions or partial exposure only partially mitigate this effect. Beyond raw performance, we identify four recurring adaptation strategies, with test-driven refinement emerging as the most frequent. These results highlight how LLMs adapt their behavior when exposed to contextual signals that conflict with explicit instructions, providing useful insight into how models reconcile pretraining objectives with alignment constraints.

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.

Code review is a fundamental process in software development that plays a pivotal role in ensuring code quality and reducing the likelihood of errors and bugs. However, code review can be complex, subjective, and time-consuming. Quality estimation , comment generation , and code refinement constitute the three key tasks of this process, and their automation has traditionally been addressed separately in the literature using different approaches. In particular, recent efforts have focused on fine-tuning pre-trained language models to aid in code review tasks, with each task being considered in isolation. We believe that these tasks are interconnected, and their fine-tuning should consider this interconnection. In this paper, we introduce a novel deep-learning architecture, named DISCOREV, which employs cross-task knowledge distillation to address these tasks simultaneously. In our approach, we utilize a cascade of models to enhance both comment generation and code refinement models. The fine-tuning of the comment generation model is guided by the code refinement model, while the fine-tuning of the code refinement model is guided by the quality estimation model. We implement this guidance using two strategies: a feedback-based learning objective and an embedding alignment objective. We evaluate DISCOREV by comparing it to state-of-the-art methods based on independent training and fine-tuning. Our results show that our approach generates better review comments, as measured by the BLEU score, as well as more accurate code refinement according to the CodeBLEU score.

Holistic consideration of the technical, psychological, and social aspects of software engineering tasks is essential. We introduce a conceptual framework designed to assess AI-driven software engineering tasks from multiple perspectives, to improve the efficiency, well-being, and psychological functioning of developers.