English(EN) SWE-Ladder: Learning to Localize, Reproduce, and Patch via Progressive Privileged Self-Distillation

新的AI方法SWE-Ladder增强软件修复能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了SWE-Ladder，一种用于训练人工智能软件工程任务代理的新方法。该方法利用渐进式特权自蒸馏，将修复过程分解为不同的阶段：本地化、复现和修复。通过提供特定阶段的证据，例如用于本地化的更改文件和用于复现的失败测试，SWE-Ladder旨在提高代理的性能。在SWE-bench基准测试中使用Qwen3-4B-Instruct-2507模型进行测试时，与GRPO和OPSD等现有方法相比，SWE-Ladder显著提高了pass@1的成功率。 AI

影响这项研究可能带来更强大的人工智能代理，用于自动化软件开发和维护。

排序理由该集群包含一篇学术论文，详细介绍了一种用于软件工程领域人工智能代理的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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; 该集群包含一篇学术论文，详细介绍了一种用于软件工程领域人工智能代理的新方法。[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, model release; 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.AI TIER_1 English(EN) · Xudong Cai, Zhengxi Lu, Yuchen Yan, Jian Shao, Jun Xiao, Yueting Zhuang, Yongliang Shen · 2026-10-27 04:00

SWE-Ladder：通过渐进式特权自蒸馏学习本地化、复现和修复

arXiv:2610.33667v1 Announce Type: new Abstract: Resolving a repository-level issue typically requires a software-engineering (SWE) agent to localize the faulty code, reproduce the failure, and patch the code. Reinforcement learning trains such agents from a single test result on …

本文如何被排名

报道来源 [1]

SWE-Ladder：通过渐进式特权自蒸馏学习本地化、复现和修复

相关实体

相关话题