# LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks

arXiv: https://arxiv.org/abs/2606.10294 · HTML: https://mlsanity.com/paper/2606.10294/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 60 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits](https://mlsanity.com/paper/2107.10845/) (2021)
- [LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization](https://mlsanity.com/paper/2306.01102/) (2023)
- [HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark](https://mlsanity.com/paper/2103.10584/) (2021)
- [Can GPT-4 Perform Neural Architecture Search?](https://mlsanity.com/paper/2304.10970/) (2023)
- [Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks](https://mlsanity.com/paper/2205.08501/) (2022)
- [AutoSNN: Towards Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2201.12738/) (2022)
- [NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies](https://mlsanity.com/paper/2210.03230/) (2022)
- [Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators](https://mlsanity.com/paper/1911.00139/) (2019)
- [Quantum Architecture Search: A Survey](https://mlsanity.com/paper/2406.06210/) (2024)
- [L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization](https://mlsanity.com/paper/2110.14807/) (2021)
- [Uncertainty Modeling of Emerging Device-based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Search](https://mlsanity.com/paper/2107.06871/) (2021)
- [An Electro-Photonic System for Accelerating Deep Neural Networks](https://mlsanity.com/paper/2109.01126/) (2021)
- [AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing](https://mlsanity.com/paper/2305.10459/) (2023)
- [AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator](https://mlsanity.com/paper/2111.06503/) (2021)
- [GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model](https://mlsanity.com/paper/2305.05351/) (2023)
- [XploreNAS: Explore Adversarially Robust & Hardware-efficient Neural Architectures for Non-ideal Xbars](https://mlsanity.com/paper/2302.07769/) (2023)
- [AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing](https://mlsanity.com/paper/2506.18495/) (2025)

## Abstract (arXiv)

Deploying neural networks on unconventional hardware demands architectures that co-optimize task accuracy and platform-specific constraints such as energy cost, physical non-idealities, and numerical precision. Existing neural architecture search (NAS) methods are typically tailored to a single hardware family, limiting cross-platform comparison and generalization. We introduce Unconventional Hardware Neural Architecture Search (UH-NAS), a hardware-agnostic, LLM-guided NAS framework that integrates language models as evolutionary operators to co-optimize accuracy and inference energy. By exposing hardware as a swappable backend with per-platform energy models, physical constraints, and non-ideality simulators, UH-NAS enables fair system-level comparisons across various backends without modifying the search algorithm. Tested on optical MZI hardware, UH-NAS discovers more diverse, robust architectures than conventional baselines while outperforming existing LLM-to-NAS approaches. Additional ablations on architecture robustness under non-idealities and the role of system prompts highlight the importance of architecture-hardware co-design for emerging computing platforms.