---
id: 20261023-T0-09
title: "用 AI 研究团队自动搜索线性注意力新架构"
title_en: "AI Research Teams Autonomously Search for Linear Attention Architectures"
url: https://ai.daily.yangsir.net/daily/20261023-T0-09
issue_date: 2026-10-23
publish_date: 2026-10-22T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2610.28887
---

# 用 AI 研究团队自动搜索线性注意力新架构

论文探索用协作式 AI 研究者团队自动发现线性注意力架构：多个智能体分工提出想法、修改代码、运行实验。为解决搜索容易陷入局部最优的问题，团队设计了鼓励多样性的机制。这类工作的意义在于把架构搜索从人工试错转为可并行的自动化流程，若方法可迁移，未来新架构的产出速度可能不再受限于人手。

## English Version

**AI Research Teams Autonomously Search for Linear Attention Architectures**

The paper explores using teams of collaborative AI researchers to autonomously discover linear attention architectures, with agents dividing work across idea generation, code modification, and experiment execution. To avoid getting stuck in local minima, the authors design mechanisms that encourage diversity in the search. The significance lies in shifting architecture search from manual trial-and-error to a parallelizable automated process. If the approach generalizes, the pace of new architecture discovery may no longer be capped by human headcount.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2610.28887)

**详情页**：https://ai.daily.yangsir.net/daily/20261023-T0-09

---

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