Evaluating Verified Autonomy in Quantum Engineering
Abstract
Reliable quantum engineering is essential for turning quantum phenomena into practical technologies. As quantum platforms grow in scale and complexity, their characterization and operation require increasing human effort and coordination. Scientific artificial intelligence agents, which can plan experiments, operate instruments, and analyze observations, offer a promising route towards autonomous quantum engineering. Yet whether current agents can perform reliably in this setting has not been systematically established. To fill this gap, we developed Quantum-Harbor, a virtual laboratory that provides a controlled execution environment for agents to interact with quantum systems. This design enables direct verification of both the actions taken and the conclusions drawn. Building on this framework, we introduce QIQCBench, a benchmark of $49$ expert-authored tasks spanning multiple layers including calibration and control, error correction and compilation, sensing and networking. Across $17$ frontier agentic systems, QIQCBench reveals wide variation in verified performance. These results expose a substantial gap between demonstrating capability and achieving reliable operation, and establish Quantum-Harbor as a foundation for measuring progress towards verified autonomy in quantum engineering.
Related
- A quantitative model for embedding quantum-secure communications and evaluating communication autonomy in industrial control systems
- Verified Pauli-Product Measurement Compilation for Fault-Tolerant Quantum Computation
- QEncodeBench: Can Large Language Models Encode Classical Problems into Verified Quantum Oracles?
- Modular optical fault-tolerant quantum computation via an interface between verified resources and online logical operations
- Quantum algorithm for evaluating Lyapunov stability of non-Hermitian systems
BibTeX
@misc{guo2026evaluating,
title = {{Evaluating Verified Autonomy in Quantum Engineering}},
author = {Naixu Guo and Changhao Li and Siyu Cheng and Qicheng Tang and Binzhao Luo and Bikun Li and Yuxuan Du and Shihao Ru and Jiaqi Cai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.17439},
eprint = {2609.17439},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.17439},
}
RIS
TY - UNPB
TI - Evaluating Verified Autonomy in Quantum Engineering
AU - Naixu Guo
AU - Changhao Li
AU - Siyu Cheng
AU - Qicheng Tang
AU - Binzhao Luo
AU - Bikun Li
AU - Yuxuan Du
AU - Shihao Ru
AU - Jiaqi Cai
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.17439
UR - https://arxiv.org/abs/2609.17439
AB - Reliable quantum engineering is essential for turning quantum phenomena into practical technologies. As quantum platforms grow in scale and complexity, their characterization and operation require increasing human effort and coordination. Scientific artificial intelligence agents, which can plan experiments, operate instruments, and analyze observations, offer a promising route towards autonomous quantum engineering. Yet whether current agents can perform reliably in this setting has not been systematically established. To fill this gap, we developed Quantum-Harbor, a virtual laboratory that provides a controlled execution environment for agents to interact with quantum systems. This design enables direct verification of both the actions taken and the conclusions drawn. Building on this framework, we introduce QIQCBench, a benchmark of $49$ expert-authored tasks spanning multiple layers including calibration and control, error correction and compilation, sensing and networking. Across $17$ frontier agentic systems, QIQCBench reveals wide variation in verified performance. These results expose a substantial gap between demonstrating capability and achieving reliable operation, and establish Quantum-Harbor as a foundation for measuring progress towards verified autonomy in quantum engineering.
ER -