Toward Quantum Software Automation: A Quantum-Aware Harness for LLM-Guided Evolution

2026-09-29

AI Summary

This study addresses the reliance of quantum software design on manual heuristics and the lack of quantum awareness in existing large language model (LLM) search approaches by proposing the QSA framework. This method leverages evolution-difficulty-guided kernel set optimization to direct evolutionary search, integrates static and snapshot analyses to provide fine-grained context, and constructs task-specific reward mechanisms tailored for both compilation and runtime stages, thereby enabling LLM-driven automated quantum software design. Experimental evaluations conducted on the IBM Quantum platform demonstrate that QSA improves quantum processing unit (QPU) utilization by 4.2%–9.5%, enhances circuit fidelity by 15.2%–19.5%, and reduces error mitigation overhead by over 96.8%.

Abstract

Quantum software is critical for improving the efficiency and reliability of scarce quantum hardware. However, its design still relies heavily on ad-hoc, handcrafted heuristics that are often suboptimal and quickly become obsolete as quantum hardware evolves. LLM-guided evolutionary search offers a promising way to automatically explore complex software designs, but existing search frameworks lack the quantum-specific support needed for efficient evolution: verification is expensive, feedback is sparse, and heterogeneous quantum programs require different optimization objectives. In this paper, we present QSA, a quantum-aware harness for LLM-guided evolutionary search toward automating quantum software design. QSA equips the search with three forms of quantum-specific guidance: an evolution-hardness-guided coreset and approximate scoring to reduce verification cost, static and snapshot analyses to provide fine-grained execution context, and task-specific rewards for compiler passes and runtime policies. We evaluate QSA on the IBM Quantum platform across three benchmark suites. For multiprogramming, QSA improves QPU utilization by 4.2%-9.5% and Hellinger fidelity by 15.2%-19.5% over the state of the art. For error mitigation, QSA reduces mitigation time by at least 96.8% while achieving comparable or better fidelity. These gains require only $6.9 in LLM API cost over 11.3 hours.

Problem

• Quantum software automation
• LLM-guided evolutionary search
• Quantum-aware harness
• Verification cost
• Heterogeneous quantum programs

Innovation

• Quantum Software Automation
• LLM-Guided Evolutionary Search
• Quantum-Aware Harness
• Approximate Scoring
• Task-Specific Rewards