arXiv cs.LG + cs.RO + cs.HC· Wei Xiong, Jiangtong Li, Han Zhao, Linxiao Yang, Jie Li, Changjun Jiang·· 2 天前AI 评分55
NeuroAct 用双环自主研究框架提升 EEG 分析与解码
NeuroAct: Advancing EEG Analysis and Decoding via Dual-Loop Autonomous Research
AI 导读
作者提出 NeuroAct，一个面向 EEG 分析与解码的自主研究代理框架，通过内环的研究、开发、评审角色与将结果蒸馏为条件化建议的外环协同工作。
正文 · 原文
Abstract:EEG analysis and decoding underpin brain-computer interfaces, cognitive assessment, and sleep monitoring. Fixed pipelines and reward-driven search do not explicitly determine how signal structure, representations, predictor behavior, and training dynamics contribute to performance or generalization gaps, leaving intervention choice underdetermined. We introduce NeuroAct, an autonomous research agent framework for EEG analysis and decoding. NeuroAct implements dual-loop autonomous research across EEG foundation models, task-specific predictors, and model combinations. In an inner loop, research, development, and review roles use evidence on signal structure, representations, predictor behavior, and training dynamics to test hypotheses, select analyses or interventions, and refine candidates using performance, stability, and cost feedback. An outer loop distills outcomes into conditional, testable recommendations with task and model conditions, then validates and revises them on subsequent this http URL evaluate four settings: (A) EEG General Analysis, (B) Cross-task Model Optimization, (C) Single-task Open Research, and (D) Collaborative Prediction. In Setting A, NeuroAct's 80.88 macro-average exceeds BrainAgent's 63.13 by 17.75 points. In Setting B, NeuroAct raises EEGPT's mean balanced accuracy (BA) by 7.34 points and HBN Pearson's (r) from 0.6894 to 0.7362; in Setting C, it improves ADFTD BA by 16.33 points; and in Setting D, it raises Workload BA from 79.69% to 85.02%. Experience reuse raises BCIC-IV-2a BA from 34.66% to 50.81% while reducing LLM tokens by 64.02%, indicating recommendations improve cross-task performance. NeuroAct enables evidence-guided EEG research improved by cross-task experience.
| Comments: | 30 pages, 8 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.25211 [cs.LG] |
| (or arXiv:2610.25211v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.25211 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wei Xiong [view email]
[v1]
Sun, 18 Oct 2026 12:09:42 UTC (4,639 KB)
来源：arXiv cs.LG + cs.RO + cs.HC · arxiv.org