Leveraging LLM-Based Agentic Systems to Generate Quantum Applications for Test Optimization
2026-07-01 • Software Engineering
Software Engineering
AI summaryⓘ
The authors present QPipe, a system that uses multiple specialized AI agents to turn everyday language instructions into working quantum computing programs. They tested QPipe on 20 real-world problems and found it could reliably produce and run quantum code, often outperforming traditional optimization methods. The system works best when it keeps knowledge about coding, task details, feedback from code reviews, and splits tasks among agents. Their work shows that coordinating AI agents can help make complex quantum software more accessible and effective.
quantum computingsoftware engineeringlarge language modelsnatural language processingmulti-agent systemscode generationtest optimizationgenetic algorithmsworkflow automation
Authors
Ming Tao, Yuechen Li, Tao Yue, Man Zhang, Aitor Arrieta Marcos
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.