Leveraging LLM-Based Agentic Systems to Generate Quantum Applications for Test Optimization

2026-07-01

AI Summary

This work addresses the high barrier to entry in quantum programming, which typically demands specialized expertise, by introducing QPipe—the first end-to-end framework based on multi-agent collaboration that automatically translates natural language descriptions of test optimization requirements into executable and traceable quantum workflows. QPipe employs a team of specialized agents with clearly defined roles to collaboratively handle requirement parsing, modeling, code generation, review, and verification. Experimental evaluation on 20 real-world tasks demonstrates that QPipe achieves a 100% code compilation success rate and a 96.7% execution success rate, with most generated solutions outperforming an offline genetic algorithm baseline. The framework produces correct and practical quantum programs in an average time of 260.1 seconds, significantly enhancing both correctness and usability.

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.

Problem

• quantum application generation
• natural language requirements
• test optimization
• software engineering
• quantum computing

Innovation

• LLM-based agentic systems
• quantum application generation
• test optimization
• multi-agent coordination
• natural language to quantum code