摘要：操作原子力显微镜（AFM）等科学仪器需要持续作出专家级决策。经过训练的用户需要定义实验意图，将其转化为仪器命令，评估输入数据，调整成像参数，并对最终图像进行后处理。现有自动化方案通常仅通过硬编码例程、特定任务控制器或训练后的机器学习模型，覆盖该工作流中的部分环节。本文提出了一种 Agentic AI 框架，通过 Model Context Protocol（MCP）将通用、工具增强型大语言模型连接至仪器功能，从而操作 AFM 工作流中可执行的部分。该框架由 3 个基于 MCP 的 Agent 构成：AFM Messenger 将自然语言指令转换为经检查的仪器命令；AFM Pilot 通过大语言模型（LLM）评估图像质量，并在必要时调整成像参数；AFM Doctor 则诊断图像伪影，并从预先批准的工具集中执行透明的后处理。由于语言模型执行图像评估，而非依赖固定标量目标或外部优化器，因此同一策略可跨越不同样品类型和成像模式应用，无需专门重新训练。硬件操作安全性通过执行前的歧义检查层得到保障。与微调模型及现成的工具调用模型相比，基准测试表明，降低错误命令执行至零的关键在于这一受防护的执行层，而不只是模型能力。在针对不同样品的实时实验中，AFM Pilot 在图像质量、迭代次数和调参时间方面均与专家操作人员相当，且不存在显著差异。这些结果展示了一条让科学仪器实现 Agentic 操作的安全路径：实验意图仍由人类定义，而命令执行、基于图像的调参和后处理则委托给 AI Agent。

Abstract:Operating a scientific instrument such as an atomic force microscope (AFM) requires continuous expert decision-making. A trained user defines the experimental intent, translates it into instrument commands, assesses incoming data, adjusts imaging parameters, and post-processes the final image. Existing automation usually addresses only parts of this workflow through hard-coded routines, task-specific controllers, or trained machine-learning models. Here we present an agentic-AI framework that operates the executable part of the AFM workflow using a general-purpose, tool-augmented large language model connected to instrument functions through the Model Context Protocol (MCP). The framework consists of 3 MCP-based agents: AFM Messenger converts natural-language instructions into checked instrument commands; AFM Pilot assesses image quality through a large language model (LLM) and, if necessary, adapts imaging parameters; and AFM Doctor diagnoses image artifacts and applies transparent post-processing from a pre-approved tool set. Because the language model performs image assessment rather than a fixed scalar objective or external optimizer, the same strategy can be applied across sample types and imaging modes without specific retraining. Safe hardware operation is enforced through an ambiguity check layer before execution. Benchmarking against fine-tuned and off-the-shelf tool-using models shows that this guarded execution layer, rather than model capability alone, reduces wrong-command execution to zero. In live experiments on different samples, AFM Pilot matched expert operators in image quality, iteration count, and tuning time, with no significant difference. These results demonstrate a safe route to agentic operation of scientific instruments, where experimental intent remains human-defined while command execution, image-based tuning, and post-processing are delegated to AI agents.