Leveraging Mutation Analysis for LLM-based Repair of Quantum Programs

2026-01-18

AI Summary

This work addresses the low repair success rates and poor interpretability of patches commonly observed in existing automated quantum program repair approaches. It proposes a novel framework that, for the first time, integrates mutation analysis as contextual information into a large language model–driven repair pipeline. By synergistically combining static analysis, dynamic execution, and mutation outcomes, the method designs a multidimensional prompting strategy to simultaneously generate both repaired code and natural language explanations. Experimental results demonstrate a 94.4% repair success rate, alongside significantly improved quality of generated explanations, thereby achieving a strong balance between effectiveness and interpretability.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Quantum Machine Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In recent years, Automated Program Repair (APR) techniques specifically designed for quantum programs have been proposed. However, existing approaches often suffer from low repair success rates or poor understandability of the generated patches. In this study, we construct a framework in which a large language model (LLM) generates code repairs along with a natural language explanation of the applied repairs. To investigate how the contextual information included in prompts influences APR performance for quantum programs, we design four prompt configurations with different combinations of static information, dynamic information, and mutation analysis results. Mutation analysis evaluates how small changes to specific parts of a program affect its execution results and provides more detailed dynamic information than simple execution outputs such as stack traces. Our experimental results show that mutation analysis can provide valuable contextual information for LLM-based APR of quantum programs, improving repair success rates (achieving 94.4% in our experiment) and in some cases also improving the quality of generated explanations. Our findings point toward new directions for developing APR techniques for quantum programs that enhance both reliability and explainability.

Problem

• Automated Program Repair
• Quantum Programs
• Repair Success Rate
• Patch Understandability
• Large Language Model

Innovation

• Mutation Analysis
• Large Language Model
• Automated Program Repair
• Quantum Programs
• Explainable AI