KQFuzz: Knowledge-Guided Fuzzing for Quantum Libraries via Large Language Models

📄 arXiv: 2607.25647v1 📥 PDF

作者: Fuyuan Xia, Qixin Zhang, Chenhao Ying, Haojin Zhu, Shuai Wang, Yuan Luo, Pingchuan Ma, Yuxuan Du

分类: cs.SE, cs.AI, cs.MA, quant-ph

发布日期: 2026-07-28

备注: Accepted to the 41st IEEE/ACM International Conference on Automated Software Engineering. 17 pages, 9 figures. Comments are welcome

💡 一句话要点

提出KQFuzz以解决量子库模糊测试效率低下问题

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 量子计算 模糊测试 大型语言模型 代码库知识 测试生成 量子库 软件可靠性

📋 核心要点

  1. 现有的LLM基础模糊测试方法在灵活性和效率上存在不足，限制了量子库的测试能力。
  2. KQFuzz通过引入知识引导的模糊测试策略，结合适应性评估和变异策略，提升了测试生成的质量和效率。
  3. 实验结果显示，KQFuzz在多个量子库上的覆盖率显著提高，并成功发现了13个bug，12个已被修复。

📝 摘要（中文）

随着量子计算的不断进步，确保量子库的可靠性和正确性变得愈发重要。为此，许多基于大型语言模型（LLM）的模糊测试方法被提出以发现潜在的bug。然而，这些方法仍存在灵活性不足和效率低下等局限，阻碍了量子计算领域的发展。为了解决这些挑战，本文提出了KQFuzz，这是一种新颖的知识引导模糊测试工具，旨在通过综合代码库知识来增强LLM基础的测试生成。KQFuzz结合了适应性评估和两级变异策略，以探索复杂的执行路径并触发潜在的bug。实验结果表明，KQFuzz在Qiskit、PennyLane和Cirq等流行量子库上的覆盖率提高了18.44%。

🔬 方法详解

问题定义：本文旨在解决现有基于LLM的模糊测试方法在灵活性和效率上的不足，特别是在量子库的测试中，如何有效发现潜在bug是一个亟待解决的问题。

核心思路：KQFuzz的核心思路是利用代码库的知识引导模糊测试，通过高效生成高质量的量子种子程序，并结合适应性评估和变异策略来探索复杂的执行路径。

技术框架：KQFuzz的整体架构包括三个主要模块：知识引导的种子程序生成模块、适应性评估模块和变异策略模块。首先，通过特定的提示方案生成种子程序，然后对其进行评估和变异，以提高测试的多样性和覆盖率。

关键创新：KQFuzz的主要创新在于其知识引导的提示方案，能够有效整合代码库知识，从而生成更具针对性的测试用例。这一设计与传统的模糊测试方法相比，显著提高了测试的效率和效果。

关键设计：在KQFuzz中，设计了特定的提示方案以适应量子程序的特性，同时在评估和变异策略中引入了两级变异机制，以增强生成测试用例的多样性和有效性。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

KQFuzz在对Qiskit、PennyLane和Cirq等量子库的模糊测试中，覆盖率提高了最高达18.44%。此外，KQFuzz成功发现了13个bug，所有bug均已确认，其中12个已被开发者修复，显示了其在实际应用中的有效性。

🎯 应用场景

KQFuzz在量子计算领域具有广泛的应用潜力，能够有效提高量子库的测试效率和可靠性。随着量子计算技术的发展，确保量子软件的正确性和稳定性将变得尤为重要，KQFuzz的研究成果将为量子软件开发提供重要支持，推动量子计算的实际应用。

📄 摘要（原文）

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 still suffer from limitations such as insufficient flexibility and low efficiency, which hinder the progress of the quantum computing field. To address these challenges, we propose KQFuzz, a novel knowledge-guided fuzzer for quantum libraries. It leverages comprehensive codebase knowledge to ground LLM-based test generation, synergizing this with fitness-guided evaluation and two-level mutations to explore complex execution paths and trigger potential bugs. Firstly, KQFuzz introduces a novel prompting scheme tailored to quantum programs, which strategically incorporates knowledge of the codebase to efficiently generate high-quality quantum seed programs. Moreover, we develop evaluation and mutation strategies to handle the generated seed programs, facilitating efficient fuzzing execution while further enriching the diversity of the resulting test cases. We implement KQFuzz and conduct fuzzing on three popular quantum libraries, including Qiskit, PennyLane, and Cirq. Experimental results demonstrate that our approach significantly outperforms other state-of-the-art methods, with coverage improved by up to 18.44%. During the development of KQFuzz, we discovered 13 bugs, all of which have been confirmed and 12 have already been fixed by the developers.