Agents for self-driving laboratories applied to quantum computing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916975258632192 |
|---|---|
| author | Cao, Shuxiang Zhang, Zijian Alghadeer, Mohammed Fasciati, Simone D Piscitelli, Michele Bakr, Mustafa Leek, Peter Aspuru-Guzik, Alán |
| author_facet | Cao, Shuxiang Zhang, Zijian Alghadeer, Mohammed Fasciati, Simone D Piscitelli, Michele Bakr, Mustafa Leek, Peter Aspuru-Guzik, Alán |
| contents | Fully automated self-driving laboratories are promising to enable high-throughput and large-scale scientific discovery by reducing repetitive labour. However, effective automation requires deep integration of laboratory knowledge, which is often unstructured, multimodal, and difficult to incorporate into current AI systems. This paper introduces the k-agents framework, designed to support experimentalists in organizing laboratory knowledge and automating experiments with agents. Our framework employs large language model-based agents to encapsulate laboratory knowledge including available laboratory operations and methods for analyzing experiment results. To automate experiments, we introduce execution agents that break multi-step experimental procedures into agent-based state machines, interact with other agents to execute each step and analyze the experiment results. The analyzed results are then utilized to drive state transitions, enabling closed-loop feedback control. To demonstrate its capabilities, we applied the agents to calibrate and operate a superconducting quantum processor, where they autonomously planned and executed experiments for hours, successfully producing and characterizing entangled quantum states at the level achieved by human scientists. Our knowledge-based agent system opens up new possibilities for managing laboratory knowledge and accelerating scientific discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07978 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Agents for self-driving laboratories applied to quantum computing Cao, Shuxiang Zhang, Zijian Alghadeer, Mohammed Fasciati, Simone D Piscitelli, Michele Bakr, Mustafa Leek, Peter Aspuru-Guzik, Alán Artificial Intelligence Quantum Physics Fully automated self-driving laboratories are promising to enable high-throughput and large-scale scientific discovery by reducing repetitive labour. However, effective automation requires deep integration of laboratory knowledge, which is often unstructured, multimodal, and difficult to incorporate into current AI systems. This paper introduces the k-agents framework, designed to support experimentalists in organizing laboratory knowledge and automating experiments with agents. Our framework employs large language model-based agents to encapsulate laboratory knowledge including available laboratory operations and methods for analyzing experiment results. To automate experiments, we introduce execution agents that break multi-step experimental procedures into agent-based state machines, interact with other agents to execute each step and analyze the experiment results. The analyzed results are then utilized to drive state transitions, enabling closed-loop feedback control. To demonstrate its capabilities, we applied the agents to calibrate and operate a superconducting quantum processor, where they autonomously planned and executed experiments for hours, successfully producing and characterizing entangled quantum states at the level achieved by human scientists. Our knowledge-based agent system opens up new possibilities for managing laboratory knowledge and accelerating scientific discovery. |
| title | Agents for self-driving laboratories applied to quantum computing |
| topic | Artificial Intelligence Quantum Physics |
| url | https://arxiv.org/abs/2412.07978 |