---
id: 20260712-T0-06
title: "Agentic NAS：用LLM智能体自动设计神经网络架构"
title_en: "Agentic NAS: LLM Agents Automate Neural Network Architecture Design"
url: https://ai.daily.yangsir.net/daily/20260712-T0-06
issue_date: 2026-07-12
publish_date: 2026-07-11T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2607.07984
---

# Agentic NAS：用LLM智能体自动设计神经网络架构

新论文提出Agentic Neural Architecture Search（Agentic NAS），利用大语言模型（LLM）替代传统手动设计的搜索空间。该方法让智能体自主探索和发现网络结构，减少对领域专家经验的依赖，可自动适配新任务，避免每次都重新构建搜索空间。

## English Version

**Agentic NAS: LLM Agents Automate Neural Network Architecture Design**

A new paper introduces Agentic Neural Architecture Search (Agentic NAS), using LLMs to replace manually engineered search spaces. The agent autonomously explores and discovers architectures, reducing reliance on domain expertise and enabling automatic adaptation to new tasks.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2607.07984)

**详情页**：https://ai.daily.yangsir.net/daily/20260712-T0-06

---

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