Llmguided Neural Architecture Search For Robust Codesign Of Physical Neural Networks

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

**arXiv ID:** 2606.10294
**Authors:** Tyler King, Timothee Leleu
**Published:** 2026-06-09T01:32:17Z
**Abstract:**
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.

## Skill Description

This skill is generated from the arXiv paper: LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks (2606.10294).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2606.10294](http://arxiv.org/abs/2606.10294v1)