Related papers: BugPilot: Complex Bug Generation for Efficient Lea…

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…

Bugs are essential in software engineering; many research studies in the past decades have been proposed to detect, localize, and repair bugs in software systems. Effectiveness evaluation of such techniques requires complex bugs, i.e.,…

Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development. However, in the absence of large annotated corpora, training these analyses is…

Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers, which rely on mathematical logic and symbolic reasoning…

Bugs are inescapable during software development due to frequent code changes, tight deadlines, etc.; therefore, it is important to have tools to find these errors. One way of performing bug identification is to analyze the characteristics…

Large Language Models (LLMs) for code have gained significant attention recently. They can generate code in different programming languages based on provided prompts, fulfilling a long-lasting dream in Software Engineering (SE), i.e.,…

LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four…

Recent research builds various patching agents that combine large language models (LLMs) with non-ML tools and achieve promising results on the state-of-the-art (SOTA) software patching benchmark, SWE-bench. Based on how to determine the…

Debugging is an essential skill when learning to program, yet its instruction and emphasis often vary widely across introductory courses. In the era of code-generating large language models (LLMs), the ability for students to reason about…

Bug severity prediction is important in software maintenance, because it helps the development teams to prioritize bugs that have a significant impact on the operation, stability and security of the system. In large software projects bug…

Progress in software-engineering agents is increasingly constrained by the scarcity of executable, scalable, and realistic data for training and evaluation. This scarcity stems from three fundamental challenges in existing pipelines:…

Deep learning has recently achieved initial success in program analysis tasks such as bug detection. Lacking real bugs, most existing works construct training and test data by injecting synthetic bugs into correct programs. Despite…

Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub…

Bug triage is an important step in the process of bug fixing. The goal of bug triage is to assign a new-coming bug to the correct potential developer. The existing bug triage approaches are based on machine learning algorithms, which build…

Automated test generators, such as search based software testing (SBST) techniques, replace the tedious and expensive task of manually writing test cases. SBST techniques are effective at generating tests with high code coverage. However,…

One of the primary mechanisms by which developers receive feedback about in-field failures of software from users is through bug reports. Unfortunately, the quality of manually written bug reports can vary widely due to the effort required…

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…

Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action…

Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have…

We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g.,…