---
id: 20261001-T0-11
title: "EEGAgentBench：首个评测LLM agent做脑电分析能力的基准"
title_en: "EEGAgentBench: First Benchmark for LLM Agents on EEG Analysis Tasks"
url: https://ai.daily.yangsir.net/daily/20261001-T0-11
issue_date: 2026-10-01
publish_date: 2026-09-30T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2609.31632
---

# EEGAgentBench：首个评测LLM agent做脑电分析能力的基准

研究者发布EEGAgentBench，这是首个专门评测LLM agent在脑电图（EEG）分析中表现的基准测试。EEG分析正从短片段分类向长时程解读演进，需要迭代式证据积累、多步推理和多种信号处理工具的协同使用。现有基准主要针对短片段分类任务，无法评估agent在长时程、多步骤EEG分析中的能力。EEGAgentBench覆盖短时程和长时程两类任务，测试agent能否像人类专家一样逐步分析信号、调用专业工具并得出诊断结论。该基准为EEG分析领域引入AI agent提供了标准化的评估框架。

## English Version

**EEGAgentBench: First Benchmark for LLM Agents on EEG Analysis Tasks**

Researchers release EEGAgentBench, the first benchmark designed to evaluate LLM agents on electroencephalography (EEG) analysis. EEG analysis is shifting from short-segment classification toward long-horizon interpretation requiring iterative evidence accumulation, multi-step reasoning, and coordinated use of specialized signal-processing tools. Existing benchmarks focus on short-segment classification and cannot assess agent capabilities in long-horizon, multi-step EEG analysis. EEGAgentBench covers both short- and long-horizon tasks, testing whether agents can progressively analyze signals, invoke specialized tools, and reach diagnostic conclusions like human experts. The benchmark provides a standardized evaluation framework for AI agents in EEG analysis.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2609.31632)

**详情页**：https://ai.daily.yangsir.net/daily/20261001-T0-11

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*