中文
相关论文

相关论文: Are Benchmark Tests Strong Enough? Mutation-Guided…

200 篇论文

The SWE-Bench Verified leaderboard is approaching saturation, with the top system achieving 78.80%. However, we show that this performance is inflated. Our re-evaluation reveals that one in five "solved" patches from the top-30 agents are…

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

Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of…

软件工程 · 计算机科学 2026-05-22 Yuxuan Sun , Yuze Zhao , Yufeng Wang , Yao Du , Zhiyuan Ma , Jinbo Wang , Mengdi Zhang , Kai Zhang , Zhenya Huang

Code Agent development is an extremely active research area, where a reliable performance metric is critical for tracking progress and guiding new developments. This demand is underscored by the meteoric rise in popularity of SWE-Bench.…

软件工程 · 计算机科学 2025-03-12 Konstantinos Vergopoulos , Mark Niklas Müller , Martin Vechev

Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…

软件工程 · 计算机科学 2026-05-15 Man Ho Lam , Chaozheng Wang , Hange Liu , Jingyu Xiao , Haau-sing Li , Jen-tse Huang , Terry Yue Zhuo , Michael R. Lyu

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…

软件工程 · 计算机科学 2026-04-08 Kai Yu , Zhenhao Zhou , Junhao Zeng , Ying Wang , Xueying Du , Zhiqiang Yuan , Junwei Liu , Ziyu Zhou , Yujia Wang , Chong Wang , Xin Peng

Test suites in real-world projects are often large and achieve high code coverage, yet they remain insufficient for detecting all bugs. The abundance of unresolved issues in open-source project trackers highlights this gap. While regression…

软件工程 · 计算机科学 2026-05-12 Yang Chen , Toufique Ahmed , Reyhaneh Jabbarvand , Martin Hirzel

As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full…

软件工程 · 计算机科学 2026-05-08 Ye Shang , Quanjun Zhang , Haichuan Hu , Chunrong Fang , Liang Xiao , Zhenyu Chen

Test-based automated program repair has been a prolific field of research in software engineering in the last decade. Many approaches have indeed been proposed, which leverage test suites as a weak, but affordable, approximation to program…

The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world…

软件工程 · 计算机科学 2025-06-12 Boxi Yu , Yuxuan Zhu , Pinjia He , Daniel Kang

Current benchmarks for evaluating software engineering agents, such as SWE-Bench Verified, are predominantly derived from GitHub issues and fail to accurately reflect how developers interact with chat-based coding assistants in integrated…

软件工程 · 计算机科学 2026-01-27 Spandan Garg , Benjamin Steenhoek , Yufan Huang

Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are costly to refresh. Scalable evaluation of open-ended items…

计算与语言 · 计算机科学 2026-03-24 Yandan Zheng , Haoran Luo , Zhenghong Lin , Wenjin Liu , Luu Anh Tuan

Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al. introduced the SWE-bench dataset, which comprises 2,294…

软件工程 · 计算机科学 2024-10-11 Reem Aleithan , Haoran Xue , Mohammad Mahdi Mohajer , Elijah Nnorom , Gias Uddin , Song Wang

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

Among the many different kinds of program repair techniques, one widely studied family of techniques is called test suite based repair. Test-suites are in essence input-output specifications and are therefore typically inadequate for…

软件工程 · 计算机科学 2017-03-02 Zhongxing Yu , Matias Martinez , Benjamin Danglot , Thomas Durieux , Martin Monperrus

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…

Mutation testing has been demonstrated to be one of the most powerful fault-revealing tools in the tester's tool kit. Much previous work implicitly assumed it to be sufficient to re-compute mutant suites per release. Sadly, this makes…

软件工程 · 计算机科学 2022-12-23 Milos Ojdanic , Mike Papadakis , Mark Harman

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…

The rapid iteration cycles of modern live-service games make regression testing indispensable for maintaining quality and stability. However, existing regression testing approaches face critical limitations, especially in common gray-box…

软件工程 · 计算机科学 2025-12-02 Jinyu Cai , Jialong Li , Nianyu Li , Zhenyu Mao , Mingyue Zhang , Kenji Tei

As agent capabilities advance, existing benchmarks, such as $\tau^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which…

人工智能 · 计算机科学 2026-05-28 Tomer Keren , Nitay Calderon , Asaf Yehudai , Yotam Perlitz , Michal Shmueli-Scheuer , Roi Reichert
‹ 上一页 1 2 3 10 下一页 ›