用大模型在单张显卡上高效搜索神经网络结构，不需调参也不靠云平台。
Resource-Efficient Iterative LLM-Based NAS with Feedback Memory
- 用反馈记忆池记录每次尝试的问题、修改和结果，失败也当学习信号。
- 三款7B以下大模型在18小时内从28%提升到71.5%准确率，仅用一张4090显卡。
- 双模型分工协作，自动生成代码并诊断问题，适合边缘部署的轻量设计。
神经网络架构搜索（NAS）可自动化设计网络，但传统方法需大量计算资源。本文提出一种闭环流程，利用大语言模型（LLM）在单张消费级显卡上迭代生成、评估并优化卷积神经网络架构，无需微调大模型。核心是受马尔可夫链启发的历史反馈记忆：滑动窗口大小为 $K{=}5$，保持上下文稳定且提供足够学习信号。不同于以往丢弃失败路径的LLM优化器，每个历史条目均为结构化诊断三元组——记录发现的问题、建议修改及结果，将代码执行失败视为第一类学习信号。采用双模型分工降低认知负荷：代码生成器负责产出可运行的PyTorch架构，提示改进器专注诊断推理。由于大模型与架构训练共享有限显存，搜索过程自然偏好紧凑、硬件高效的模型，适合边缘部署。我们在三个冻结的指令微调大模型（≤7B参数）上，基于单轮代理准确率（CIFAR-10、CIFAR-100、ImageNette）进行最多2000次迭代的无约束开放代码空间搜索。在CIFAR-10上，DeepSeek-Coder-6.7B从28.2%提升至69.2%，Qwen2.5-7B从50.0%提升至71.5%，GLM-5从43.2%提升至62.0%。完整2000次搜索仅耗时约18小时（单张RTX 4090），建立了一种低成本、可复现且硬件感知的LLM驱动NAS范式，无需云端基础设施。
原文摘要 · Abstract (English)
Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures for image classification on a single consumer-grade GPU without LLM fine-tuning. Central to our approach is a historical feedback memory inspired by Markov chains: a sliding window of $K{=}5$ recent improvement attempts keeps context size constant while providing sufficient signal for iterative learning. Unlike prior LLM optimizers that discard failure trajectories, each history entry is a structured diagnostic triple -- recording the identified problem, suggested modification, and resulting outcome -- treating code execution failures as first-class learning signals. A dual-LLM specialization reduces per-call cognitive load: a Code Generator produces executable PyTorch architectures while a Prompt Improver handles diagnostic reasoning. Since both the LLM and architecture training share limited VRAM, the search implicitly favors compact, hardware-efficient models suited to edge deployment. We evaluate three frozen instruction-tuned LLMs (${\leq}7$B parameters) across up to 2000 iterations in an unconstrained open code space, using one-epoch proxy accuracy on CIFAR-10, CIFAR-100, and ImageNette as a fast ranking signal. On CIFAR-10, DeepSeek-Coder-6.7B improves from 28.2% to 69.2%, Qwen2.5-7B from 50.0% to 71.5%, and GLM-5 from 43.2% to 62.0%. A full 2000-iteration search completes in ${\approx}18$ GPU hours on a single RTX~4090, establishing a low-budget, reproducible, and hardware-aware paradigm for LLM-driven NAS without cloud infrastructure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。