PulseAugur
EN
LIVE 07:47:58

KQFuzz uses LLMs to improve quantum library testing, finding 13 bugs

By PulseAugur Editorial · [2 sources] ·

Researchers have developed KQFuzz, a new method for testing quantum libraries that utilizes large language models (LLMs) guided by codebase knowledge. This approach aims to improve the flexibility and efficiency of LLM-based fuzzing, which has previously been limited. KQFuzz employs a novel prompting scheme that incorporates knowledge of the quantum program's codebase to generate high-quality seed programs. The system also includes evaluation and mutation strategies to enhance test case diversity and fuzzing efficiency. When applied to Qiskit, PennyLane, and Cirq, KQFuzz demonstrated a significant improvement in coverage, up to 18.44%, and helped identify 13 confirmed bugs, 12 of which have already been fixed. AI

IMPACT Enhances the reliability of quantum computing libraries by improving bug detection efficiency.

RANK_REASON The cluster describes a new research paper detailing a novel method for testing quantum libraries.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

KQFuzz uses LLMs to improve quantum library testing, finding 13 bugs

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

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

    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…

RELATED ENTITIES

RELATED TOPICS