发表机构
Nanyang Technological University; The University of Hong Kong; Southeast University（南洋理工大学; 香港大学; 东南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AutoBCI通过设计智能体和预测智能体自动发现脑电解码架构，在14个数据集上以64.16%的平均平衡准确率超越最强基线，并显著降低性能预测误差。
AI 中文摘要
基于脑电的脑机接口支持广泛的应用，然而设计在不同任务中表现良好的解码架构仍然具有挑战性。我们引入了AutoBCI，一个智能体框架，其中设计智能体和预测智能体支持跨任务的脑电解码架构的发现和选择。设计智能体执行池引导的架构发现（PGAD），通过多个脑电任务（如情绪识别、运动想象和睡眠分期）的训练和验证来生成和优化架构。预测智能体执行基于早期知识的性能估计（PEEK），利用架构代码、训练协议和早期学习曲线来预测全预算验证性能，并选择有前景的候选者进行持续训练。跨越涵盖运动想象、情绪识别和睡眠分期的14个脑电数据集，我们使用六个大语言模型（包括Opus 5.5和GPT 5.6 Sol）评估AutoBCI，并将搜索过程选择的架构与十个基线进行比较：六个传统脑电模型和四个基础模型。AutoBCI与Claude Opus 5.5发现的架构实现了64.16%的平均测试平衡准确率（bAcc），而该指标上最强的基线REVE为63.87%。使用十个观察到的周期，PEEK将预测平均验证bAcc的平均绝对误差从2.20个百分点降低到1.36个百分点，相对于最佳观测得分基线减少了38.1%。
英文摘要
EEG-based brain-computer interfaces support a broad range of applications, yet designing decoding architectures that perform well across diverse tasks remains challenging. We introduce AutoBCI, an agentic framework in which a Designer Agent and a Forecaster Agent support the discovery and selection of EEG decoding architectures across tasks. The Designer Agent performs Pool-Guided Architecture Discovery (PGAD), generating and refining architectures through training and validation across multiple EEG tasks, such as emotion recognition, motor imagery, and sleep staging. The Forecaster Agent performs Performance Estimation from Early Knowledge (PEEK), using architecture code, the training protocol, and early learning curves to predict full-budget validation performance and select promising candidates for continued training. Across 14 EEG datasets spanning motor imagery, emotion recognition, and sleep staging, we evaluate AutoBCI with six LLMs, including Opus 5.5 and GPT 5.6 Sol, and compare the architectures selected by the search procedure against ten baselines: six conventional EEG models and four foundation models. The architecture discovered by AutoBCI with Claude Opus 5.5 achieves 64.16% average test balanced accuracy (bAcc), compared with 63.87% for REVE, the strongest baseline on this metric. Using ten observed epochs, PEEK reduces mean absolute error in predicting average validation bAcc from 2.20 to 1.36 percentage points, a 38.1% reduction relative to the best-observed-score baseline.
Comments34 pages, 6 figures, including supplementary material
