A Protocol-Guided LLM Agent for Quantum Program Synthesis and Execution
Abstract
This study evaluates a protocol-guided large language model (LLM) agent workflow for quantum program synthesis and execution. A versioned YAML protocol specifies interface and quantum-semantic requirements while leaving circuit design to the model. The workflow combines Qiskit circuit generation, evaluator-guided repair, and quantum processing unit (QPU) deployment. A matched ablation evaluates four LLM endpoints using the variational quantum eigensolver (VQE) for H2, the quantum approximate optimization algorithm (QAOA) for MaxCut, and Fashion-MNIST quantum-kernel classification. Across 240 trials, protocol guidance increased evaluator completion from 80.0\% to 99.2\%, reduced mean repairs from 2.56 to 0.75, and reduced mean agent time from 55.70 to 30.58~s. Provider-reported token use decreased for three of four endpoints. Completed VQE trials meeting chemical accuracy increased from 16/40 to 29/40, while valid QAOA approximation ratios remained comparable. Semantic review identified rank-one fidelity kernels, reinforcing the distinction between evaluator completion and semantic validity. A 210-run IBM QPU study evaluated the combined generation-and-selection pipelines and confirmed deployment feasibility. The results support protocol guidance as a software-reliability layer that must be complemented by quantum-semantic validation.
Related
- Fault-tolerant execution of error-corrected quantum algorithms
- BAHAMAS: A Control Plane for Optimization and Execution of Variational Quantum Circuits
- An Efficient Quantum Circuit for Flow Model Execution Using Quantum Neural Networks
- C-Phase-Aware Compilation for Efficient Fault-Tolerant Quantum Execution
- Arbitrarily Loss-Tolerant Quantum Position Verification in a Single Execution
BibTeX
@misc{ho2026protocolguided,
title = {{A Protocol-Guided LLM Agent for Quantum Program Synthesis and Execution}},
author = {Ming-Kang Ho and Tai-Yue Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20258},
eprint = {2609.20258},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20258},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Protocol-Guided LLM Agent for Quantum Program Synthesis and Execution
AU - Ming-Kang Ho
AU - Tai-Yue Li
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.20258
UR - https://arxiv.org/abs/2609.20258
AB - This study evaluates a protocol-guided large language model (LLM) agent workflow for quantum program synthesis and execution. A versioned YAML protocol specifies interface and quantum-semantic requirements while leaving circuit design to the model. The workflow combines Qiskit circuit generation, evaluator-guided repair, and quantum processing unit (QPU) deployment. A matched ablation evaluates four LLM endpoints using the variational quantum eigensolver (VQE) for H_2, the quantum approximate optimization algorithm (QAOA) for MaxCut, and Fashion-MNIST quantum-kernel classification. Across 240 trials, protocol guidance increased evaluator completion from 80.0\% to 99.2\%, reduced mean repairs from 2.56 to 0.75, and reduced mean agent time from 55.70 to 30.58~s. Provider-reported token use decreased for three of four endpoints. Completed VQE trials meeting chemical accuracy increased from 16/40 to 29/40, while valid QAOA approximation ratios remained comparable. Semantic review identified rank-one fidelity kernels, reinforcing the distinction between evaluator completion and semantic validity. A 210-run IBM QPU study evaluated the combined generation-and-selection pipelines and confirmed deployment feasibility. The results support protocol guidance as a software-reliability layer that must be complemented by quantum-semantic validation.
ER -