LLM-based Multi-Agent Copilot for Quantum Sensor

TL;DR

This paper introduces QCopilot, an LLM-based multi-agent system that automates quantum sensor design and diagnosis, achieving significant speedups and autonomous anomaly detection in experiments.

Contribution

The paper presents QCopilot, a novel multi-agent framework integrating external knowledge and active learning for quantum sensor development, enabling autonomous experimentation and diagnosis.

Findings

Generated 10^8 atoms in hours with no human intervention.

Achieved ~100x speedup over manual experiments.

Autonomously identified anomalous parameters in experiments.

Abstract

Large language models (LLM) exhibit broad utility but face limitations in quantum sensor development, stemming from interdisciplinary knowledge barriers and involving complex optimization processes. Here we present QCopilot, an LLM-based multi-agent framework integrating external knowledge access, active learning, and uncertainty quantification for quantum sensor design and diagnosis. Comprising commercial LLMs with few-shot prompt engineering and vector knowledge base, QCopilot employs specialized agents to adaptively select optimization methods, automate modeling analysis, and independently perform problem diagnosis. Applying QCopilot to atom cooling experiments, we generated 10${}^{\rm{8}}$ sub-$\rm{\mu}$K atoms without any human intervention within a few hours, representing $\sim$100$\times$ speedup over manual experimentation. Notably, by continuously accumulating prior knowledge and enabling dynamic modeling, QCopilot can autonomously identify anomalous parameters in multi-parameter experimental settings. Our work reduces barriers to large-scale quantum sensor deployment and readily extends to other quantum information systems.