Related papers: RepoCoder: Repository-Level Code Completion Throug…

Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on end-to-end tasks such as issue resolution truly reflects repository context reasoning, the…

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the…

How can we identify similar repositories and clusters among a large online archive, such as GitHub? Determiningrepository similarity is an essential building block in studying the dynamics and the evolution of such software ecosystems. The…

Some recently developed code large language models (Code LLMs) have been pre-trained on repository-level code data (Repo-Code LLMs), enabling these models to recognize repository structures and utilize cross-file information for code…

Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into…

This paper presents a multi-stage reranking system for repository-level code search, which leverages the vastly available commit histories of large open-source repositories to aid in bug fixing. We define the task of repository-level code…

Code generation is a latency-sensitive task that demands high timeliness. However, with the growing interest and inherent difficulty in repository-level code generation, most existing code generation studies focus on improving the…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LLMs are quite…

Large Language Models (LLMs) have recently shown remarkable progress in code generation, yet their ability to construct complete software repositories from scratch remains poorly understood. A fundamental bottleneck is the lack of…

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) for code generation. Many benchmarks like HumanEval and…

Software developers write a lot of source code and documentation during software development. Intrinsically, developers often recall parts of source code or code summaries that they had written in the past while implementing software or…

Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed…

Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow…

Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved strong performance at the function and file levels, real-world software engineering requires…

Large language models excel at generating individual functions or single files of code, yet generating complete repositories from scratch remains a fundamental challenge. This capability is key to building coherent software systems from…

Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering. Existing deep-learning approaches model code…

Repository-level code completion has drawn great attention in software engineering, and several benchmark datasets have been introduced. However, existing repository-level code completion benchmarks usually focus on a limited number of…

Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted,…

As text and code resources have expanded, large-scale pre-trained models have shown promising capabilities in code generation tasks, typically employing supervised fine-tuning with problem statement-program pairs. However, increasing model…