中文
相关论文

相关论文: SWE-Factory: Your Automated Factory for Issue Reso…

200 篇论文

Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limited by the complexity of environment setup, unit test…

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…

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…

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…

软件工程 · 计算机科学 2026-02-04 Yisen Xu , Jinqiu Yang , Tse-Hsun , Chen

SWE-Bench-Verified, a dataset comprising 500 issues, serves as a de facto benchmark for evaluating various large language models (LLMs) on their ability to resolve GitHub issues. But this benchmark may overlap with model training data. If…

软件工程 · 计算机科学 2025-12-23 Thanosan Prathifkumar , Noble Saji Mathews , Meiyappan Nagappan

AI-driven software development has rapidly advanced with the emergence of software development agents that leverage large language models (LLMs) to tackle complex, repository-level software engineering tasks. These agents go beyond just…

软件工程 · 计算机科学 2026-04-10 Zhi Chen , Wei Ma , Lingxiao Jiang

Prior works on training software engineering agents have explored utilizing existing resources such as issues on GitHub repositories to construct software engineering tasks and corresponding test suites. These approaches face two key…

软件工程 · 计算机科学 2026-01-13 Yiqi Zhu , Apurva Gandhi , Graham Neubig

Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that…

Automated issue solving seeks to autonomously identify and repair defective code snippets across an entire codebase. SWE-Bench has emerged as the most widely adopted benchmark for evaluating progress in this area. While LLM-based agentic…

软件工程 · 计算机科学 2025-09-18 Simiao Liu , Fang Liu , Liehao Li , Xin Tan , Yinghao Zhu , Xiaoli Lian , Li Zhang

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…

软件工程 · 计算机科学 2026-02-09 Yaxin Du , Yuzhu Cai , Yifan Zhou , Cheng Wang , Yu Qian , Xianghe Pang , Qian Liu , Yue Hu , Siheng Chen

Autonomous systems for software engineering are now capable of fixing bugs and developing features. These systems are commonly evaluated on SWE-bench (Jimenez et al., 2024a), which assesses their ability to solve software issues from GitHub…

Automatically resolving software issues is crucial for software development in practice, impacting the software quality and user experience. The process of resolving real-world issues encompasses tasks such as question-answering (QA), fault…

软件工程 · 计算机科学 2024-11-28 Ruida Hu , Chao Peng , Jingyi Ren , Bo Jiang , Xiangxin Meng , Qinyun Wu , Pengfei Gao , Xinchen Wang , Cuiyun Gao

Large language models (LLMs) have transformed the software engineering landscape. Recently, numerous LLM-based agents have been developed to address real-world software issue fixing tasks. Despite their state-of-the-art performance, Despite…

软件工程 · 计算机科学 2026-03-10 Xin-Cheng Wen , Binbin Chen , Haoxuan Lan , Hang Yu , Peng Di , Cuiyun Gao

Researchers have made significant progress in automating the software development process in the past decades. Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use…

软件工程 · 计算机科学 2024-07-26 Yuntong Zhang , Haifeng Ruan , Zhiyu Fan , Abhik Roychoudhury

We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test Writing (90 tasks), and Refactoring (70 tasks). SWE Atlas differs from prior SWE…

Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavor: developers interpret high-level…

软件工程 · 计算机科学 2026-05-25 Tue Le , Minh V. T. Thai , Dung Nguyen Manh , Huy Phan Nhat , Nghi D. Q. Bui

Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on popular repositories…

Automated issue solving aims to resolve real-world issues in software repositories. The most popular benchmarks for automated issue solving are SWE-bench and its human-filtered subset SWE-bench Verified. These benchmarks leverage testing to…

软件工程 · 计算机科学 2025-09-10 You Wang , Michael Pradel , Zhongxin Liu

A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically.…

软件工程 · 计算机科学 2026-01-26 Toufique Ahmed , Jatin Ganhotra , Avraham Shinnar , Martin Hirzel

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,…