HERA autonomously measures quantum devices matching expert conclusions
HERA: Assessing an Autonomous Agent for Quantum Device Measurement
Artificial Intelligence
Summary
Measuring tiny quantum devices in the lab is tricky and needs expert knowledge. The authors introduced HERA, a smart software agent that uses a special knowledge base to perform these measurements on its own. They tested HERA by having it measure and analyze graphene devices, showing its results agreed with a human expert’s. HERA also adapted to study superconductivity in a new material after some expert help, demonstrating it can work on different experiments. This shows language models combined with tailored knowledge can do careful lab science.
What this means in practice
- •For quantum device engineers: Enable autonomous measurement and analysis of quantum devices to accelerate experimental workflows without constant expert oversight.
- •For materials characterization teams: Provide a framework that adapts to new experimental protocols for discovering and analyzing material properties autonomously after minimal expert setup.
Authors
Zachary W. Gomez, Nathan Bittner, Jordan T. McCourt, Qingrui Cao, Sandesh S. Kalantre, Benjamin H. Alexander, Zhiren Zheng, Kenji Watanabe, Takashi Taniguchi, Aaron Sharpe
Abstract
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.