Agents for self-driving laboratories applied to quantum computing
arXiv:2412.07978 · doi:10.1016/j.patter.2025.101372
Abstract
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.
References in corpus (18)
- Scaling Laws for Neural Language Models
- Suppressing quantum errors by scaling a surface code logical qubit
- Gemini: A Family of Highly Capable Multimodal Models
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Quantum error correction below the surface code threshold
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- A concise review of Rydberg atom based quantum computation and quantum simulation
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- Quantum Error Correction of Qudits Beyond Break-even
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
- Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
- Native two-qubit gates in fixed-coupling, fixed-frequency transmons beyond cross-resonance interaction
- Emulating two qubits with a four-level transmon qudit for variational quantum algorithms
- A Comprehensive Study of Knowledge Editing for Large Language Models
- Long-context LLMs Struggle with Long In-context Learning
- Efficient characterization of qudit logical gates with gate set tomography using an error-free Virtual-Z-gate model
- Demonstration of quantum computation and error correction with a tesseract code
- A theory of understanding for artificial intelligence: composability, catalysts, and learning