DeQompile: quantum circuit decompilation using genetic programming for explainable quantum architecture search

2025-04-11

AI Summary

Current quantum architecture search (QAS) yields low-level quantum circuits with poor interpretability, severely limiting scalability and cross-domain applicability on noisy intermediate-scale quantum (NISQ) devices. To address this, we propose DeQompile—the first genetic programming–based quantum circuit decompilation framework—integrating symbolic regression with abstract syntax tree (AST) manipulation to reverse-compile low-level quantum assembly into high-level, human-readable Qiskit algorithms. Our approach uniquely unifies interpretability, generalizability, and verifiability of QAS outputs. Experiments demonstrate that DeQompile successfully reconstructs multiple benchmark quantum algorithms, substantially enhancing semantic comprehensibility of quantum circuits and enabling online learning integration. The framework is publicly released as open-source software.

Technology Category

• Machine Learning: Quantum Machine Learning
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Demonstrating quantum advantage using conventional quantum algorithms remains challenging on current noisy gate-based quantum computers. Automated quantum circuit synthesis via quantum machine learning has emerged as a promising solution, employing trainable parametric quantum circuits to alleviate this. The circuit ansatz in these solutions is often designed through reinforcement learning-based quantum architecture search when the domain knowledge of the problem and hardware are not effective. However, the interpretability of these synthesized circuits remains a significant bottleneck, limiting their scalability and applicability across diverse problem domains. This work addresses the challenge of explainability in quantum architecture search (QAS) by introducing a novel genetic programming-based decompiler framework for reverse-engineering high-level quantum algorithms from low-level circuit representations. The proposed approach, implemented in the open-source tool DeQompile, employs program synthesis techniques, including symbolic regression and abstract syntax tree manipulation, to distill interpretable Qiskit algorithms from quantum assembly language. Validation of benchmark algorithms demonstrates the efficacy of our tool. By integrating the decompiler with online learning frameworks, this research potentiates explainable QAS by fostering the development of generalizable and provable quantum algorithms.

Problem

• Enhancing interpretability in quantum architecture search
• Reverse-engineering high-level algorithms from low-level circuits
• Improving scalability of automated quantum circuit synthesis

Innovation

• Genetic programming decompiles quantum circuits
• Symbolic regression enhances circuit interpretability
• Abstract syntax tree manipulates Qiskit algorithms