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

Code completion can help developers improve efficiency and ease the development lifecycle. Although code completion is available in modern integrated development environments (IDEs), research lacks in determining what makes a good context…

Recent advancements in Large Language Models (LLMs) have transformed code generation from natural language queries. However, despite their extensive knowledge and ability to produce high-quality code, LLMs often struggle with contextual…

This paper introduces CodeQUEST, a novel framework leveraging Large Language Models (LLMs) to iteratively evaluate and enhance code quality across multiple dimensions, including readability, maintainability, efficiency, and security. The…

Developers often refactor source code to improve its quality during software development. A challenge in refactoring is to determine if it can be applied or not. To help with this decision-making process, we aim to search for past…

Duplicated code has a negative impact on the quality of software systems and should be detected at least. In this paper, we discuss an approach that improves source code retrieval using the structural information about the programs. We…

Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only…

Reverse engineering of binary executables is a critical problem in the computer security domain. On the one hand, malicious parties may recover interpretable source codes from the software products to gain commercial advantages. On the…

This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318 code completion tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 29 standalone…

Traditional code search engines often do not perform well with natural language queries since they mostly apply keyword matching. These engines thus require carefully designed queries containing information about programming APIs for code…

In modern software engineering, build systems play the crucial role of facilitating the conversion of source code into software artifacts. Recent research has explored high-level causes of build failures, but has largely overlooked the…

Given a large and evolving codebase, the ability to automatically generate holistic, architecture-aware documentation that captures not only individual functions but also cross-file, cross-module, and system-level interactions remains an…

Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but…

Recent advances have demonstrated the promising capabilities of large language models (LLMs) in generating register-transfer level (RTL) code, such as Verilog. However, existing LLM-based frameworks still face significant challenges in…

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative…

Publicly available source-code libraries are continuously growing and changing. This makes it impossible for models of code to keep current with all available APIs by simply training these models on existing code repositories. Thus,…

The drive for reproducibility in the computational sciences has provoked discussion and effort across a broad range of perspectives: technological, legislative/policy, education, and publishing. Discussion on these topics is not new, but…

Automated code completion, aiming at generating subsequent tokens from unfinished code, has been significantly benefited from recent progress in pre-trained Large Language Models (LLMs). However, these models often suffer from coherence…

Fast compilation is important when compilation occurs at runtime, such as query compilers in modern database systems and WebAssembly virtual machines in modern browsers. We present copy-and-patch, an extremely fast compilation technique…

Large Language Models (LLMs) have recently emerged as capable coding assistants that operate over large codebases through either agentic exploration or full-context generation. Existing benchmarks capture a broad range of coding…

Repository-level code completion is challenging as it involves complicated contexts from multiple files in the repository. To date, researchers have proposed two technical categories to enhance LLM-based repository-level code completion,…