English(EN) Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations

研究发现LLM代码修复可能引入静默错误

作者 PulseAugur 编辑部 · [2 个来源] · 2026-11-05 16:41

一项新研究表明，大型语言模型（LLM）在API迁移后修复代码时可能会引入静默错误。即使代码修复通过了典型的测试输入并能干净地执行，它们也可能产生不正确的结果。研究人员发现，专门的边缘输入和盲审程序显著降低了错误修复的发生率，但仍有相当一部分有缺陷的代码通过了这些检查。 AI

影响强调了在生产环境中，对LLM生成的代码需要更强大的测试和验证方法。

排序理由学术论文，详细介绍了关于LLM代码修复失败的研究。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 学术论文，详细介绍了关于LLM代码修复失败的研究。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, safety; 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: 5 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang · 2026-11-06 05:00

接受但错误：API迁移后LLM代码修复的沉默失败

arXiv:2611.08269v1 Announce Type: cross Abstract: After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it. We report a preregistered study of 73 tasks covering 60 documented changes …
Hugging Face Daily Papers TIER_1 English(EN) · 2026-11-05 16:41

接受但错误：API迁移后LLM代码修复的隐性失败

After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it. We report a preregistered study of 73 tasks covering 60 documented changes in CPython, Node.js and SQLite. Every candidate is…