NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines

2026-02-13

AI Summary

This work addresses the challenges of deploying foundation models in EEG analysis, which are hindered by high data and parameter demands, while generic AutoML approaches often lack neuroscientific priors, yielding solutions with poor interpretability. To bridge this gap, the authors formulate the EEG analysis pipeline design as a constrained discrete optimization problem, uniquely embedding neuroscientific priors into the evolutionary search space. By integrating domain-aware subspace initialization, a multi-objective evolutionary algorithm, and a self-reflection mechanism, the proposed method dynamically balances performance, efficiency, and novelty. Evaluated across five heterogeneous EEG benchmarks, the approach automatically generates lightweight pipelines that match the performance of large-scale foundation models, significantly outperform task-specific methods, and drastically reduce parameter counts—demonstrating strong generalizability across tasks and datasets.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Deep Neural Architectures and Foundation Models
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Although foundation models have demonstrated remarkable success in general domains, the application of these models to electroencephalography (EEG) analysis is constrained by substantial data requirements and high parameterization. These factors incur prohibitive computational costs, thereby impeding deployment in resource-constrained clinical environments. Conversely, general-purpose automated machine learning frameworks are often ill-suited for this domain, as exploration within an unbounded programmatic space fails to incorporate essential neurophysiological priors and frequently yields solutions that lack scientific plausibility. To address these limitations, we propose NeuroWeaver, a unified autonomous evolutionary agent designed to generalize across diverse EEG datasets and tasks by reformulating pipeline engineering as a discrete constrained optimization problem. Specifically, we employ a Domain-Informed Subspace Initialization to confine the search to neuroscientifically plausible manifolds, coupled with a Multi-Objective Evolutionary Optimization that dynamically balances performance, novelty, and efficiency via self-reflective refinement. Empirical evaluations across five heterogeneous benchmarks demonstrate that NeuroWeaver synthesizes lightweight solutions that consistently outperform state-of-the-art task-specific methods and achieve performance comparable to large-scale foundation models, despite utilizing significantly fewer parameters.

Problem

• EEG analysis
• foundation models
• automated machine learning
• neurophysiological priors
• computational cost

Innovation

• NeuroWeaver
• evolutionary optimization
• domain-informed initialization
• EEG analysis
• constrained programmatic search