Leveraging Reward Models for Guiding Code Review Comment Generation

• URL: http://arxiv.org/abs/2506.04464v1
• Date: Wed, 04 Jun 2025 21:31:38 GMT
• Title: Leveraging Reward Models for Guiding Code Review Comment Generation
• Authors: Oussama Ben Sghaier, Rosalia Tufano, Gabriele Bavota, Houari Sahraoui,
• Abstract summary: Code review is a crucial component of modern software development, involving the evaluation of code quality, providing feedback on potential issues, and refining the code to address identified problems.<n>Deep learning techniques are able to tackle the generative aspect of code review, by commenting on a given code as a human reviewer would do.<n>In this paper, we introduce CoRAL, a deep learning framework automating review comment generation by exploiting reinforcement learning with a reward mechanism.
• Score: 13.306560805316103
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Code review is a crucial component of modern software development, involving the evaluation of code quality, providing feedback on potential issues, and refining the code to address identified problems. Despite these benefits, code review can be rather time consuming, and influenced by subjectivity and human factors. For these reasons, techniques to (partially) automate the code review process have been proposed in the literature. Among those, the ones exploiting deep learning (DL) are able to tackle the generative aspect of code review, by commenting on a given code as a human reviewer would do (i.e., comment generation task) or by automatically implementing code changes required to address a reviewer's comment (i.e., code refinement task). In this paper, we introduce CoRAL, a deep learning framework automating review comment generation by exploiting reinforcement learning with a reward mechanism considering both the semantics of the generated comments as well as their usefulness as input for other models automating the code refinement task. The core idea is that if the DL model generates comments that are semantically similar to the expected ones or can be successfully implemented by a second model specialized in code refinement, these comments are likely to be meaningful and useful, thus deserving a high reward in the reinforcement learning framework. We present both quantitative and qualitative comparisons between the comments generated by CoRAL and those produced by the latest baseline techniques, highlighting the effectiveness and superiority of our approach.

Related papers

• MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks [56.34018316319873]
  We propose MERA Code, a benchmark for evaluating code for the latest code generation LLMs in Russian.<n>This benchmark includes 11 evaluation tasks that span 8 programming languages.<n>We evaluate open LLMs and frontier API models, analyzing their limitations in terms of practical coding tasks in non-English languages.
  arXiv  Detail & Related papers  (2025-07-16T14:31:33Z)
• CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models [10.108114365564926]
  State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks.<n>Code review comments are often implicit, ambiguous, and colloquial, requiring models to grasp both code and human intent.<n>This challenge calls for evaluating large language models' ability to bridge both technical and conversational contexts.
  arXiv  Detail & Related papers  (2025-03-20T14:07:31Z)
• Harnessing Large Language Models for Curated Code Reviews [2.5944208050492183]
  In code review, generating structured and relevant comments is crucial for identifying code issues and facilitating accurate code changes.<n>Existing code review datasets are often noisy and unrefined, posing limitations to the learning potential of AI models.<n>We propose a curation pipeline designed to enhance the quality of the largest publicly available code review dataset.
  arXiv  Detail & Related papers  (2025-02-05T18:15:09Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• Leveraging Reviewer Experience in Code Review Comment Generation [11.224317228559038]
  We train deep learning models to imitate human reviewers in providing natural language code reviews. The quality of the model generated reviews remain sub-optimal due to the quality of the open-source code review data used in model training. We propose a suite of experience-aware training methods that utilise the reviewers' past authoring and reviewing experiences as signals for review quality.
  arXiv  Detail & Related papers  (2024-09-17T07:52:50Z)
• AI-Assisted Assessment of Coding Practices in Modern Code Review [11.803776132972029]
  AutoCommenter is an end-to-end system for learning and enforcing coding best practices. This paper reports on the development, deployment, and evaluation of AutoCommenter.
  arXiv  Detail & Related papers  (2024-05-22T11:57:18Z)
• Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective [85.48043537327258]
  We propose MANGO (comMents As Natural loGic pivOts), including a comment contrastive training strategy and a corresponding logical comment decoding strategy. Results indicate that MANGO significantly improves the code pass rate based on the strong baselines. The robustness of the logical comment decoding strategy is notably higher than the Chain-of-thoughts prompting.
  arXiv  Detail & Related papers  (2024-04-11T08:30:46Z)
• Improving the Learning of Code Review Successive Tasks with Cross-Task Knowledge Distillation [1.0878040851638]
  We introduce a novel deep-learning architecture, named DISCOREV, which employs cross-task knowledge distillation to address these tasks simultaneously. We 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.
  arXiv  Detail & Related papers  (2024-02-03T07:02:22Z)
• Exploring the Advances in Identifying Useful Code Review Comments [0.0]
  This paper reflects the evolution of research on the usefulness of code review comments. It examines papers that define the usefulness of code review comments, mine and annotate datasets, study developers' perceptions, analyze factors from different aspects, and use machine learning classifiers to automatically predict the usefulness of code review comments.
  arXiv  Detail & Related papers  (2023-07-03T00:41:20Z)
• ReCode: Robustness Evaluation of Code Generation Models [90.10436771217243]
  We propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt.
  arXiv  Detail & Related papers  (2022-12-20T14:11:31Z)
• ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
  We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
  arXiv  Detail & Related papers  (2022-03-15T08:25:08Z)
• Deep Just-In-Time Inconsistency Detection Between Comments and Source Code [51.00904399653609]
  In this paper, we aim to detect whether a comment becomes inconsistent as a result of changes to the corresponding body of code. We develop a deep-learning approach that learns to correlate a comment with code changes. We show the usefulness of our approach by combining it with a comment update model to build a more comprehensive automatic comment maintenance system.
  arXiv  Detail & Related papers  (2020-10-04T16:49:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.