QPipe: LLM-Based Agentic Quantum Application Generation for Test Optimization
Abstract
Quantum computing is increasingly explored for software engineering (SE) optimization, but translating natural-language (NL) task-level requirements into executable quantum applications still demands substantial quantum and programming expertise. We present QPipe, a large language model (LLM)-based multi-agent architecture that autonomously turns NL requirements into traceable quantum-application workflows through specialized agents for requirement parsing, formulation, code generation, review, execution, and verification. We evaluate QPipe on 20 NL requirements, each associated with a real-world benchmark and a test-optimization problem. QPipe successfully completes the key stages of quantum-application generation across requirements, achieving average rates of 100% for code compilation and 96.7% for application execution and final-result combination, with average generation costs of 260.1 seconds and 1.89M tokens per requirement. Among the generated quantum applications that execute successfully, the returned solutions outperform the offline genetic algorithm baseline in most cases. Ablation results further show that QPipe's advantage depends on retaining code-generation skills, task knowledge, review feedback, and multi-agent decomposition. These results indicate that agentic coordination can support generation of executable quantum applications for tackling test optimization problems from real-world benchmarks.
Related
- Qubit-Efficient Variational Quantum Optimization via Pauli Correlation Encoding: Application to Large-Scale Power Demand Portfolio Optimization
- Classical Verification of a Remote Quantum Processor via Degenerate Concordant Computations: An Application to Randomness Generation
- Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
- Agentic Global Optimization of Site-Disordered Crystalline Materials
- Differentiable Schwarz-Coupled Solvers for Thin Boundary Layer Transport: Inverse Modeling via Agentic AI Optimization
BibTeX
@misc{tao2026qpipe,
title = {{QPipe: LLM-Based Agentic Quantum Application Generation for Test Optimization}},
author = {Ming Tao and Yuechen Li and Tao Yue and Man Zhang and Aitor Arrieta Marcos},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2607.00939},
eprint = {2607.00939},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.00939},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - QPipe: LLM-Based Agentic Quantum Application Generation for Test Optimization
AU - Ming Tao
AU - Yuechen Li
AU - Tao Yue
AU - Man Zhang
AU - Aitor Arrieta Marcos
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2607.00939
UR - https://arxiv.org/abs/2607.00939
AB - Quantum computing is increasingly explored for software engineering (SE) optimization, but translating natural-language (NL) task-level requirements into executable quantum applications still demands substantial quantum and programming expertise. We present QPipe, a large language model (LLM)-based multi-agent architecture that autonomously turns NL requirements into traceable quantum-application workflows through specialized agents for requirement parsing, formulation, code generation, review, execution, and verification. We evaluate QPipe on 20 NL requirements, each associated with a real-world benchmark and a test-optimization problem. QPipe successfully completes the key stages of quantum-application generation across requirements, achieving average rates of 100% for code compilation and 96.7% for application execution and final-result combination, with average generation costs of 260.1 seconds and 1.89M tokens per requirement. Among the generated quantum applications that execute successfully, the returned solutions outperform the offline genetic algorithm baseline in most cases. Ablation results further show that QPipe's advantage depends on retaining code-generation skills, task knowledge, review feedback, and multi-agent decomposition. These results indicate that agentic coordination can support generation of executable quantum applications for tackling test optimization problems from real-world benchmarks.
ER -