# Resource-Efficient Iterative LLM-Based NAS with Feedback Memory

arXiv: https://arxiv.org/abs/2603.12091 · HTML: https://mlsanity.com/paper/2603.12091/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://mlsanity.com/paper/1902.09635/) (2019)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Evaluating the Search Phase of Neural Architecture Search](https://mlsanity.com/paper/1902.08142/) (2019)
- [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](https://mlsanity.com/paper/2102.01063/) (2021)
- [Speedy Performance Estimation for Neural Architecture Search](https://mlsanity.com/paper/2006.04492/) (2020)
- [Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2307.01998/) (2023)
- [LEMUR Neural Network Dataset: Towards Seamless AutoML](https://mlsanity.com/paper/2504.10552/) (2025)
- [BM-NAS: Bilevel Multimodal Neural Architecture Search](https://mlsanity.com/paper/2104.09379/) (2021)
- [NNGPT: Rethinking AutoML with Large Language Models](https://mlsanity.com/paper/2511.20333/) (2025)
- [VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?](https://mlsanity.com/paper/2504.19267/) (2025)
- [Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis](https://mlsanity.com/paper/2511.07329/) (2025)
- [A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks](https://mlsanity.com/paper/2512.04329/) (2025)
- [AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?](https://mlsanity.com/paper/2506.07216/) (2025)
- [Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design](https://mlsanity.com/paper/2512.24120/) (2025)
- [From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures](https://mlsanity.com/paper/2601.02997/) (2026)
- [LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts](https://mlsanity.com/paper/2512.14706/) (2025)
- [From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs](https://mlsanity.com/paper/2601.03808/) (2026)
- [Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models](https://mlsanity.com/paper/2601.08517/) (2026)
- [The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization](https://mlsanity.com/paper/2404.04111/) (2024)

## Built on by (most cited first, 7 of 7)

- [Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs](https://mlsanity.com/paper/2605.04903/) (2026)
- [LEMUR 2: Unlocking Neural Network Diversity for AI](https://mlsanity.com/paper/2607.06839/) (2026)
- [Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability](https://mlsanity.com/paper/2605.30103/) (2026)
- [Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search](https://mlsanity.com/paper/2606.23739/) (2026)
- [Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study](https://mlsanity.com/paper/2606.20933/) (2026)
- [Curating Same-Family Neural Networks for LLM-Guided Model Improvement: A Controlled Case Study](https://mlsanity.com/paper/2607.05704/) (2026)
- [Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures](https://mlsanity.com/paper/2607.08511/) (2026)

## Abstract (arXiv)

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 (≤7B 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 ≈18 GPU hours on a single RTX~4090, establishing a low-budget, reproducible, and hardware-aware paradigm for LLM-driven NAS without cloud infrastructure.