AI 中文总结
研究针对认知EEG分析需专业知识及选择多的问题，提出基于MNE-Python的CogEEGAgent代理，LLM解释意图，确定性组件验证控制，在基准测试等中表现良好，建立了有限自主性和可审计自动化框架。
AI 中文摘要
认知研究中的脑电图（EEG）分析需要专业知识，并涉及在对比、通道、时间窗口和统计测试等方面的多种合理选择。大语言模型（LLM）代理可以将各种自然语言问题转化为分析选择，提供灵活的自动化接口。然而，仅凭流畅的报告无法确定代理是否独立于自适应搜索选择了所需的分析或评估了确认性声明。我们提出了CogEEGAgent，这是一个基于MNE-Python的认知EEG分析代理。其特定于EEG的科学工具将语义与科学权威分开。LLM解释意图并提出注册分析，而确定性组件验证类型化合同、控制确认访问并授权基于证据的发布。在预先指定的路由基准上，CogEEGAgent比匹配的确定性路由器更准确地将语言映射到注册分析，而匹配的预检使两个系统在需要时都弃权。在外部模型编写、结果盲的活动中，完整系统发布支持的分析，并进行参与者不相交的确认，阻止预先指定的能力风险和生命周期重用请求。策略压力测试表明，保留的确认可以抑制未校正的自适应搜索产生的误报。这些研究共同建立了认知EEG工作流程的有限自主性和可审计的自动化框架。更广泛地说，它们展示了科学代理如何将灵活的语言理解与对推理和发布的故障关闭控制相结合。
英文摘要
Electroencephalography (EEG) analysis in cognitive studies requires specialized expertise and involves many defensible choices over contrasts, channels, time windows, and statistical tests. LLM agents can translate varied natural-language questions into analysis choices, offering a flexible interface for automation. Yet fluent reports alone cannot establish that an agent selected the requested analysis or evaluated a confirmatory claim independently of adaptive search. We present CogEEGAgent, a cognitive-EEG analysis agent grounded in MNE-Python. Its EEG-specific scientific harness separates semantic from scientific authority. The LLM interprets intent and proposes registered analyses, while deterministic components validate typed contracts, control confirmation access, and authorize evidence-bound release. On a prespecified routing benchmark, CogEEGAgent maps language to registered analyses more accurately than a matched deterministic router, while matched preflight makes both systems abstain whenever required. In an externally model-authored, outcome-blind campaign, the complete system releases supported analyses with participant-disjoint confirmation and blocks prespecified capability hazards and lifecycle-reuse requests. Policy stress testing shows that held-out confirmation curbs false positives from uncorrected adaptive search. Together, these studies establish bounded autonomy and an auditable automation framework for cognitive-EEG workflows. More broadly, they show how scientific agents can combine flexible language understanding with fail-closed control over inference and release.
Comments16 pages, 5 figures, and 16 tables. The supplementary material is included in the same PDF
