AI 中文总结
EasyBCI是两阶段大语言模型智能体，可针对六种信号类型规划执行脑机接口预处理，经评估其在EEG任务中表现优于人工流程及通用编码智能体，可扩展至多模态并提升可复现性。
AI 中文摘要
脑机接口将神经活动转换为设备指令，但其性能依赖的预处理工作仍为人工操作，依赖专家经验且可复现性差。大语言模型智能体可实现科学编码自动化，但现有系统缺乏神经预处理所需的模态覆盖范围、原始数据隔离、经验积累及领域监督。我们提出EasyBCI，一种两阶段大语言模型智能体，可针对六种信号类型规划并执行预处理流程。规划智能体将每个记录转化为仅含文本的“数据指纹”，且绝不向模型暴露原始数据，同时选择基于文献的操作序列；执行智能体生成、运行并自修正代码，直至满足质量标准，而质量门控经验系统会将验证过的策略保留为可复用技能。领域专家会在两个决策节点介入，在未检测到错误可能使下游分析失效的地方保留人类判断。在使用固定线性分类器的脑电（EEG）评估中，所有五种EasyBCI主干网络均比人工流程保留了更多与任务相关的可分性；在主干网络相同的比较中，EasyBCI在五种配置中的四种上，针对两种标签方案的表现均优于通用编码智能体。EasyBCI还可扩展到另外五种采样率跨度近三个数量级的模态，生成带有记录决策溯源的完整可复现流程。这些结果表明，领域特定编排可让缺乏专业 expertise 的实验室获得可审计的预处理，阐明了适用于其他科学领域AI智能体的设计原则。
英文摘要
Brain-computer interfaces translate neural activity into device commands, yet their performance hinges on preprocessing that remains manual, expert-dependent and poorly reproducible. Large language model agents can automate scientific coding, but existing systems lack the modality coverage, raw-data isolation, experience accumulation and domain oversight that neural preprocessing requires. We introduce EasyBCI, a two-phase LLM agent that plans and executes preprocessing pipelines for six signal types. A Plan Agent profiles each recording into a text-only Data Fingerprint that never exposes raw data to the model and selects a literature-grounded operator sequence. An Execution Agent generates, runs and self-corrects code until quality criteria are met, while a quality-gated experience system retains validated strategies as reusable skills. A domain expert intervenes at two decision gates, retaining human judgement where undetected error can invalidate downstream analyses. Evaluation on EEG with a fixed linear classifier shows that all five EasyBCI backbones preserve more task-relevant separability than the manual pipeline. Under same-backbone comparison, EasyBCI outperforms general-purpose coding agents on both label schemes for four of five configurations. EasyBCI extends to five additional modalities spanning nearly three orders of magnitude in sampling rate, producing complete reproducible pipelines with recorded decision provenance. These results indicate that domain-specific orchestration can bring auditable preprocessing within reach of laboratories lacking dedicated expertise, illustrating design principles applicable to AI agents in other scientific domains.
Comments15 pages, 6 figures, 3 tables
