相关论文: SWE-Tester: Training Open-Source LLMs for Issue Re…

Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks. One significant application of LLMs is in tackling software engineering challenges, particularly in resolving real-world tasks on…

Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment setup process for real-world issues suffer from low success…

Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their…

The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench and its variants have become standard in…

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…

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and…

Rigorous software testing is crucial for developing and maintaining high-quality code, making automated test generation a promising avenue for both improving software quality and boosting the effectiveness of code generation methods.…

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…

Large Language Models (LLMs) have shown strong capability in diverse software engineering tasks. However, feature-driven development, a highly prevalent real-world task that involves developing new functionalities for large, existing…

Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as…

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…

The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination…

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…

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…

Automated tools for solving GitHub issues are receiving significant attention by both researchers and practitioners, e.g., in the form of foundation models and LLM-based agents prompted with issues. A crucial step toward successfully…

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…

Large Language Models (LLMs) have recently attracted wide interest for tackling software engineering tasks. In contrast to code generation, refactoring demands precise, semantics-preserving edits that improve program structure, which also…

While there has been plenty of work on generating tests from existing code, there has been limited work on generating tests from issues. A correct test must validate the code patch that resolves the issue. This paper focuses on the scenario…

Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution…

GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia. Within this task, SWE-bench has been released to evaluate issue resolving capabilities of large…