English(EN) SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories

SWE-Tester 训练开源LLM进行问题复现测试

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了SWE-Tester，一个旨在训练开源大语言模型（LLMs）根据自然语言问题描述生成问题复现测试的新流程。该方法旨在通过简化根本原因分析和增强自动化问题解决系统来提高开发人员的生产力。在SWT-Bench Verified基准测试中，微调后的模型表现出显著的改进，成功率提高了10%，变更覆盖率提高了21%。 AI

影响增强了开源LLM在软件测试中的能力，有望改善开发人员工作流程和自动化代码解决。

排序理由该集群描述了一篇详细介绍训练开源LLM新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍训练开源LLM新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Aditya Bharat Soni, Rajat Ghosh, Vaishnavi Bhargava, Valerie Chen, Debojyoti Dutta · 2026-09-10 04:00

SWE-Tester：为真实代码库中的问题复现训练开源LLM

arXiv:2601.13713v2 Announce Type: replace-cross Abstract: Software testing is crucial for ensuring the correctness and reliability of software systems. Automated generation of issue reproduction tests from natural language issue descriptions enhances developer productivity by sim…

本文如何被排名

报道来源 [1]

SWE-Tester：为真实代码库中的问题复现训练开源LLM

相关实体

相关话题