arXiv cs.AI· Zachary W. Gomez, Nathan Bittner, Jordan T. McCourt, Qingrui Cao, Sandesh S. Kalantre, Benjamin H. Alexander, Zhiren Zheng, Kenji Watanabe, Takashi Taniguchi, Aaron Sharpe·· 3 小时前AI 评分52
HERA 智能体论文评估大语言模型自主完成量子器件低温测量
HERA: Assessing an Autonomous Agent for Quantum Device Measurement
AI 导读
arXiv 论文提出 HERA，一个依托实验室知识库执行量子器件低温输运测量的自主智能体。盲测中 HERA 在两个多层石墨烯器件上的结论均与专家封存结论一致；消融与数百次离线回放显示知识库能提升各模型的设计与推理质量，换到超导表征新体系仅需几小时专家时间即可自主完成。
正文 · 原文
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.
| Comments: | 16 pages, 5 figures, plus Supplementary Information (7 figures, 6 tables); data and code at this https URL and this https URL |
| Subjects: | Mesoscale and Nanoscale Physics (cond-mat.mes-hall); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39074 [cond-mat.mes-hall] |
| (or arXiv:2610.39074v1 [cond-mat.mes-hall] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39074 arXiv-issued DOI via DataCite |
Submission history
From: Zachary Gomez [view email]
[v1]
Thu, 29 Oct 2026 00:08:00 UTC (14,856 KB)
来源：arXiv cs.AI · arxiv.org