Related papers: Can Old Tests Do New Tricks for Resolving SWE Issu…
Node.js is one of the most popular frameworks for building web applications. As software systems mature, the cost of running their entire regression test suite can become significant. Selective Regression Testing (SRT) is a technique that…
Scaling the amount of compute used to train language models has dramatically improved their capabilities. However, when it comes to inference, we often limit models to making only one attempt at a problem. Here, we explore inference compute…
Static analysis tools, or linters, detect violation of source code conventions to maintain project readability. Those tools automatically fix specific violations while developers edit the source code. However, existing tools are designed…
Issue-reproducing tests fail on buggy code and pass once a patch is applied, thus increasing developers' confidence that the issue has been resolved and will not be re-introduced. However, past research has shown that developers often…
Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability. We present Repeton,…
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench,…
Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather…
Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs). However, the existing GitHub issue resolution data…
During the software evolution, existing features may be adversely affected by new changes, which is well known as regression errors. Maintaining a high-quality test suite is helpful to prevent regression errors, whereas it heavily depends…
Large language models (LLMs) are transforming automated program repair (APR) through agent-based approaches that localize bugs, generate patches, and verify fixes. However, the lack of high-quality, scalable training datasets, especially…
Merging other branches into the current working branch is common in collaborative software development. However, developers still heavily rely on the textual merge tools to handle the complicated merge tasks. The latent semantic merge…
Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…
Regression testing is performed to provide confidence that changes in a part of software do not affect other parts of the software. An execution of all existing test cases is the best way to re-establish this confidence. However, regression…
Bug datasets consisting of real-world bugs are important artifacts for researchers and programmers, which lay empirical and experimental foundation for various SE/PL research such as fault localization, software testing, and program repair.…
Given that Large Language Models (LLMs) are increasingly applied to automate software development, comprehensive software assurance spans three distinct goals: regression prevention, reactive reproduction, and proactive discovery. Current…
Benchmarks like SWE-bench have standardized the evaluation of Large Language Models (LLMs) on repository-level software engineering tasks. However, these efforts remain limited by manual curation, static datasets, and a focus on…
Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with…
LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…
Bug reproduction is critical in the software debugging and repair process, yet the majority of bugs in open-source and industrial settings lack executable tests to reproduce them at the time they are reported, making diagnosis and…
We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development…