HERA: Assessing an Autonomous Agent for Quantum Device Measurement

@misc{gomez2026hera,
  title = {{HERA: Assessing an Autonomous Agent for Quantum Device Measurement}},
  author = {Zachary W. Gomez and Nathan Bittner and Jordan T. McCourt and Qingrui Cao and Sandesh S. Kalantre and Benjamin H. Alexander and Zhiren Zheng and Kenji Watanabe and Takashi Taniguchi and Aaron Sharpe},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.39074},
  eprint = {2610.39074},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.39074},
  note = {CC BY 4.0},
}

TY  - UNPB
TI  - HERA: Assessing an Autonomous Agent for Quantum Device Measurement
AU  - Zachary W. Gomez
AU  - Nathan Bittner
AU  - Jordan T. McCourt
AU  - Qingrui Cao
AU  - Sandesh S. Kalantre
AU  - Benjamin H. Alexander
AU  - Zhiren Zheng
AU  - Kenji Watanabe
AU  - Takashi Taniguchi
AU  - Aaron Sharpe
PY  - 2026
DA  - 2026/10/29
PB  - arXiv
DO  - 10.48550/arxiv.2610.39074
UR  - https://arxiv.org/abs/2610.39074
AB  - Large language model agents have begun to carry out laboratory measurements, but their scientific conclusions are useful only if they hold up under scrutiny. Demonstrating this requires controlled studies because models are stochastic and the context a model is given steers its conclusions. Here we introduce HERA, an autonomous agent designed to carry out cryogenic transport measurements of quantum devices. HERA draws on a knowledge base curated by lab members that holds measurement protocols, software tools, and literature references. We assessed HERA with a blinded trial against an expert on the stacking order of two multilayer graphene devices, an ablation of its knowledge base, and hundreds of offline replays in which models designed the trial's central measurement without running it. HERA's conclusions matched the expert's sealed conclusions on both tested devices. The ablation and the replay studies measured the impact of the knowledge base across different models, showing that with it every model designed better measurements and reasoned more soundly. To test how readily HERA extends to a new problem, we tasked it with finding and characterizing superconductivity in a different material system. This required a few hours of expert time to develop a new experimental protocol, after which HERA did both autonomously. These results show that, with a knowledge base designed for the task, language model agents are capable of sound experimental science.
ER  -