Related papers: Pull Requests as a Training Signal for Repo-Level …

This paper addresses query scheduling for goal-oriented semantic communication in pull-based status update systems. We consider a system where multiple sensing agents (SAs) observe a source characterized by various attributes and provide…

Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the…

Software projects frequently use automation tools to perform repetitive activities in the distributed software development process. Recently, GitHub introduced GitHub Actions, a feature providing automated workflows for software projects.…

Testing is a critical practice for ensuring software correctness and long-term maintainability. As agentic coding tools increasingly submit pull requests (PRs), it becomes essential to understand how testing appears in these agent-driven…

Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require…

AI coding agents increasingly submit pull requests (Agentic-PRs) to open-source repositories, yet their performance is commonly assessed using merge and rejection outcomes alone. We hypothesized that these outcome labels do not reliably…

Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification design: transforming initial proposals into carefully considered…

CleanRL is an open-source library that provides high-quality single-file implementations of Deep Reinforcement Learning algorithms. It provides a simpler yet scalable developing experience by having a straightforward codebase and…

Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2) optimal scaling of test-time compute. We introduce…

A noisy training set usually leads to the degradation of the generalization and robustness of neural networks. In this paper, we propose a novel theoretically guaranteed clean sample selection framework for learning with noisy labels.…

Programming is increasingly taught using block-based languages like Scratch. While the use of blocks prevents syntax errors, learners can still make semantic mistakes, requiring feedback and help. As teachers may be overwhelmed by help…

Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code…

Code editing plays a vital role in software engineering, requiring developers to adjust existing code according to natural language instructions while keeping functionality intact and avoiding unnecessary modifications. However,…

We present a novel study analyzing the effects of various prompt loss token weights (PLW) for supervised instruction fine-tuning (SIFT). While prompt-masking (PLW = 0) is common for SIFT, some fine-tuning APIs support fractional PLWs and…

Improving software performance is an important yet challenging part of the software development cycle. Today, the majority of performance inefficiencies are identified and patched by performance experts. Recent advancements in deep learning…

Automated Program Repair (APR) uses various tools and techniques to help developers achieve functional and error-free code faster. In recent years, Large Language Models (LLMs) have gained popularity as components in APR tool chains because…

Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…

Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to differentiate between correct and incorrect code. Recent…

Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE)…

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…