PulseAugur
中
实时 11:39:00
English(EN) KQFuzz: Knowledge-Guided Fuzzing for Quantum Libraries via Large Language Models

KQFuzz 使用 LLM 改进量子库测试，发现 13 个 bug

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了 KQFuzz，一种利用代码库知识引导的大语言模型（LLM）进行量子库测试的新方法。该方法旨在提高基于 LLM 的模糊测试的灵活性和效率，而这在以前是有限的。KQFuzz 采用了一种新颖的提示方案，该方案结合了量子程序代码库的知识来生成高质量的种子程序。该系统还包括评估和变异策略，以提高测试用例的多样性和模糊测试效率。当应用于 Qiskit、PennyLane 和 Cirq 时，KQFuzz 证明了覆盖率的显著提高，最高可达 18.44%，并帮助识别了 13 个已确认的 bug，其中 12 个已修复。 AI

影响 通过提高 bug 检测效率，增强了量子计算库的可靠性。

排序理由 该集群描述了一篇详细介绍量子库测试新方法的最新研究论文。

在 arXiv cs.AI 阅读 →

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

KQFuzz 使用 LLM 改进量子库测试，发现 13 个 bug

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
该集群描述了一篇详细介绍量子库测试新方法的最新研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, product, infra
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
50 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。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Fuyuan Xia, Qixin Zhang, Chenhao Ying, Haojin Zhu, Shuai Wang, Yuan Luo, Pingchuan Ma, Yuxuan Du ·

    KQFuzz：利用大型语言模型对量子库进行知识引导的模糊测试

    arXiv:2607.25647v1 Announce Type: cross Abstract: As quantum computing continually improves, ensuring the reliability and correctness of quantum libraries has become increasingly critical. To this end, many LLM-based fuzzing approaches towards quantum libraries have been proposed…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Yuxuan Du ·

    KQFuzz：利用大型语言模型实现量子库的知识引导模糊测试

    As quantum computing continually improves, ensuring the reliability and correctness of quantum libraries has become increasingly critical. To this end, many LLM-based fuzzing approaches towards quantum libraries have been proposed to uncover potential bugs. However, these methods…

相关实体

相关话题