Related papers: RepoMirage: Probing Repository Context Reasoning i…
While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate…
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…
In recent years, large language models (LLMs) have demonstrated substantial potential in addressing automatic program repair (APR) tasks. However, the current evaluation of these models for APR tasks focuses solely on the limited context of…
Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the…
CodeLLMs have gained widespread adoption for code generation tasks, yet their capacity to handle repository-level code generation with complex contextual dependencies remains underexplored. Our work underscores the critical importance of…
Despite Retrieval-Augmented Generation improving code completion, traditional retrieval methods struggle with information redundancy and a lack of diversity within limited context windows. To solve this, we propose a resource-optimized…
Data originating from open-source software projects provide valuable information to enhance software quality. In the scope of Software Defect Prediction, one of the most challenging parts is extracting valid data about failure-prone…
Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly…
Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from the repository, they…
Evaluation of repository-aware software engineering systems is often confounded by synthetic task design, prompt leakage, and temporal contamination between repository knowledge and future code changes. We present a time-consistent…
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 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…
We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…
Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation…
Retrieval-augmented generation (RAG) has recently demonstrated considerable potential for repository-level code completion, as it integrates cross-file knowledge with in-file preceding code to provide comprehensive contexts for generation.…
The rapid development of Large Language Models (LLMs) for code generation has transformed software development by automating coding tasks with unprecedented efficiency. However, the training of these models on open-source code repositories…
Scaling up executable code data is significant for improving language models' software engineering capability. The intricate nature of the process makes it labor-intensive, time-consuming and expert-knowledge-dependent to build a large…
Repository-level software engineering tasks require large language models (LLMs) to efficiently navigate and extract information from complex codebases through multi-turn tool interactions. Existing approaches face significant limitations:…
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…
Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context drift, loss of goal information, and recurrent failure cycles,…