Tootfinder

Leveraging Reward Models for Guiding Code Review Comment Generation
Oussama Ben Sghaier, Rosalia Tufano, Gabriele Bavota, Houari Sahraoui
https://arxiv.org/abs/2506.04464

Leveraging Reward Models for Guiding Code Review Comment Generation
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 …

"The process of coding with an “agentic” LLM appears to be the process of carefully distilling all the worst parts of code review, and removing and discarding all of its benefits."
Very insightful post on #GenAI by Glyph
(Original title: I Think I’m Done Thinking About genAI For Now)

This https://arxiv.org/abs/2503.16167 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks, such as revising source code to address code reviews, hindering their practical use. Code review comments are often implicit, ambiguous, and colloquial, requiring models to grasp both code and human intent. This challenge calls for evaluating large language models' ability to bridge both technical and conversational contexts. While exis…

"The waste of having processes that create defects and then use inspection to catch them is certainly something to avoid. A significant part of the effort in code reviews should be geared toward capturing learning that can be applied to current processes to improve them so fewer bugs are created in the future.
..."

CRScore : Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Manav Nitin Kapadnis, Atharva Naik, Carolyn Rose
https://arxiv.org/abs/2506.00296

CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and RL with AI Feedback (RLAIF), offer trade-offs: RLVR provides reliable feedback for structured tasks like code generation, while RLAIF works for unstructured outputs but is subjective. We bridge this gap with CRScore++, an RL framework that leverages both LLM…

Today I deployed an #AI backed code review system as part of the @… #monorepo PR review checks.
Is it going to replace coders? No. Is it throwing up amazing ins…

This https://arxiv.org/abs/2401.16310 has been replaced.
link: https://scholar.google.com/scholar?q=a

An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors
Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security analysis tools struggle with poor generalization, high false positive rates, and coarse detection granularity. Large Language Models (LLMs) have been considered promising candidates for addressing those challenges. In this study, we conducted an empirical study to explore the potential of LLMs in detecting security defect…

This https://arxiv.org/abs/2411.03079 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation
Static Application Security Testing (SAST) tools are critical to software quality, identifying potential code issues early in development. However, they often produce false positive warnings that require manual review, slowing down development. Thus, automating false positive mitigation (FPM) is essential. The advent of Large Language Models (LLMs), with their strong abilities in natural language and code understanding, offers promising avenues for FPM. Yet current LLM-based FPM method faces tw…

Looks like github copilot PR review now supports all the languages in public preview. This will be useful for me as I commit #fsharp code a lot. In fact I had a PR today that it reviewed, found a few decent suggestions actually.