让脑电分析机器人自主决策并可审计，避免错误结果输出。
CogEEGAgent: Toward Autonomous Cognitive EEG Analysis with Grounded Execution and Selection-Aware Verification
- 用语言模型理解问题，自动匹配预注册的脑电分析方案。
- 在盲测中准确释放支持结论的分析结果，阻止不合规请求。
- 适合需要可重复、可验证脑电研究的科研人员使用。
认知研究中的脑电图（EEG）分析需专业知识，涉及对比、通道、时间窗和统计检验等多重可辩护选择。大语言模型（LLM）可将自然语言问题转化为分析选项，实现自动化接口。然而，仅生成流畅报告无法保证代理真正执行所请求分析或独立评估确认性声明。我们提出CogEEGAgent，基于MNE-Python构建的脑电分析代理。其科学框架将语义理解与科学权威分离：语言模型解析意图并提议已注册分析，确定性组件则验证类型契约、控制确认访问并授权证据绑定的释放。在预设路由基准上，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；而匹配的预检机制使两者在必要时均能拒绝响应。在外源模型作者、结果盲测的实验中，完整系统仅释放经参与者独立验证的支持性分析，并阻断预设的能力风险与生命周期重用请求。政策压力测试显示，保留确认环节能有效抑制未校正自适应搜索带来的假阳性。这些研究共同建立了认知-脑电工作流的有限自主与可审计自动化框架。更广泛地，展示了科学代理如何结合灵活的语言理解与封闭式推理与发布控制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。