EEGAgent: A Unified Framework for Automated EEG Analysis Using Large Language Models

2025-11-13

AI Summary

Existing EEG models are predominantly single-task architectures, limiting their capacity for clinical multi-task coordination and sequential reasoning. Method: We propose the first large language model (LLM)-based intelligent agent framework tailored for EEG analysis. It orchestrates specialized tools—including signal preprocessing, time-frequency feature extraction, event detection, and natural language interaction—enabling end-to-end multi-step reasoning and interpretable, clinically compliant report generation. Contribution/Results: Unlike conventional closed-task models, our framework supports cross-scenario, scalable automated analysis. Experiments across multiple public EEG datasets demonstrate accurate execution of complex analytical workflows and generation of structured, guideline-conformant reports. The framework significantly enhances flexibility, interpretability, and clinical utility in EEG analysis.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Scalable and generalizable analysis of brain activity is essential for advancing both clinical diagnostics and cognitive research. Electroencephalography (EEG), a non-invasive modality with high temporal resolution, has been widely used for brain states analysis. However, most existing EEG models are usually tailored for individual specific tasks, limiting their utility in realistic scenarios where EEG analysis often involves multi-task and continuous reasoning. In this work, we introduce EEGAgent, a general-purpose framework that leverages large language models (LLMs) to schedule and plan multiple tools to automatically complete EEG-related tasks. EEGAgent is capable of performing the key functions: EEG basic information perception, spatiotemporal EEG exploration, EEG event detection, interaction with users, and EEG report generation. To realize these capabilities, we design a toolbox composed of different tools for EEG preprocessing, feature extraction, event detection, etc. These capabilities were evaluated on public datasets, and our EEGAgent can support flexible and interpretable EEG analysis, highlighting its potential for real-world clinical applications.

Problem

• Developing a unified framework for automated multi-task EEG analysis
• Overcoming limitations of task-specific EEG models in realistic scenarios
• Leveraging LLMs to schedule tools for comprehensive EEG interpretation

Innovation

• Leveraging LLMs to schedule multiple EEG analysis tools
• Integrating EEG preprocessing and feature extraction capabilities
• Enabling multi-task EEG analysis with user interaction