Related papers: Generating refactored code accurately using reinfo…

Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCodeReasoner, a…

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

With the rapid evolution of large language models (LLM), reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization in various domains. This paper presents a systematic survey of the application of…

Refactoring is a software engineering practice that aims to improve code quality without altering program behavior. Although automated refactoring tools have been extensively studied, their practical applicability remains limited. Recent…

Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as prompt optimizers, which can generate improved task prompts via…

Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple sampling and comparisons within the policy…

A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using…

Developers often refactor code to improve the maintainability and comprehension of the software. There are many studies on refactoring activities in traditional software systems. However, refactoring in data-intensive systems is not well…

In real-world software engineering tasks, solving a problem often requires understanding and modifying multiple functions, classes, and files across a large codebase. Therefore, on the repository level, it is crucial to extract the relevant…

Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternative is Direct Policy Optimization (DPO), which replaces an…

Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto-regressive nature of LLMs, they are susceptible…

Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task because of LLMs' lack of…

Commit messages are the atomic level of software documentation. They provide a natural language description of the code change and its purpose. Messages are critical for software maintenance and program comprehension. Unlike documenting…

Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their critic-free and normalized advantage estimation. However, in…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of tasks. Nonetheless, this technique often necessitates substantial computational resources, making it impractical for deployment…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy…

Refactoring is a common practice in software development, aimed at improving the internal code structure in order to make it easier to understand and modify. Consequently, it is often assumed that refactoring makes the code less prone to…

Refactoring is a practice widely adopted during software maintenance and evolution. Due to its importance, there is extensive work on the effectiveness of refactoring in achieving code quality. However, developer's intentions are usually…