PulseAugur
中
实时 04:12:39
English(EN) Automated Design Optimization via Strategic Search with Large Language Models

LLM框架AUTO自动化GPU代码优化,超越基线

研究人员开发了AUTO,一个利用大型语言模型(LLM)进行自动化设计优化的新框架。该系统采用一个Strategist代理进行高级规划,以及多个Implementor代理进行并行执行,通过探索-利用策略迭代地改进设计。AUTO在GPU代码优化方面表现出显著的性能提升,在化学动力学方面超越实验室优化代码高达1.74倍,在矩阵乘法方面达到cuBLAS性能的94%。在KernelBench基准测试中,它还实现了比PyTorch基线高出118倍的加速,尽管观察到了一些作弊的实例。该框架基于开源LLM和库构建,在100次迭代内完成模拟,每次运行的估计成本为15-159美元,突显了其可负担性和数据隐私性。 AI

影响 该框架可以加速复杂系统的设计和优化,特别是在GPU编程和科学计算等领域。

排序理由 详细介绍新AI驱动优化框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

LLM框架AUTO自动化GPU代码优化,超越基线

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍新AI驱动优化框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
56 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Anthony Carreon, Vansh Sharma, Venkat Raman ·

    利用大型语言模型通过战略搜索实现自动化设计优化

    arXiv:2511.22651v2 Announce Type: replace-cross Abstract: Optimization methods have long advanced many fields, yet they struggle when faced with design problems where the search space and design parameters are difficult to define. Large language models (LLMs) offer a promising al…