# Automated Design Optimization via Strategic Search with Large Language Models

arXiv: https://arxiv.org/abs/2511.22651 · HTML: https://mlsanity.com/paper/2511.22651/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 17 of 17)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://mlsanity.com/paper/2310.19923/) (2023)
- [NVIDIA Tensor Core Programmability, Performance & Precision](https://mlsanity.com/paper/1803.04014/) (2018)
- [Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variables](https://mlsanity.com/paper/1910.01688/) (2019)
- [GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization](https://mlsanity.com/paper/2506.20807/) (2025)
- [Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization](https://mlsanity.com/paper/2505.23387/) (2025)
- [Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP](https://mlsanity.com/paper/2109.03777/) (2021)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [A Reliable Knowledge Processing Framework for Combustion Science using Foundation Models](https://mlsanity.com/paper/2401.00544/) (2023)
- [From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow](https://mlsanity.com/paper/2509.12443/) (2025)
- [A GPU-based Compressible Combustion Solver for Applications Exhibiting Disparate Space and Time Scales](https://mlsanity.com/paper/2510.23993/) (2025)

## Built on by (most cited first, 1 of 1)

- [Explainable AI: Learning from the Learners](https://mlsanity.com/paper/2601.05525/) (2026)

## Abstract (arXiv)

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 alternative by dynamically interpreting design spaces and leveraging encoded domain knowledge. To this end, we present AUTO: an iterative optimization framework that treats design optimization as a strategic search guided by LLM reasoning. The framework separates high-level planning by a Strategist agent from low-level implementation by concurrent Implementor agents, iteratively refining designs through explore-exploit strategies. We demonstrate AUTO on three GPU code optimization problems. For chemical kinetics, AUTO outperforms in-lab-optimized code by up to 1.74× for problem sizes up to 105 cells. For matrix multiplication, AUTO achieves up to 94% of cuBLAS double-precision performance. For KernelBench, we achieve speedups of up to 118× over PyTorch baselines across 29 problems spanning individual operators and full neural network architectures; however, cheating was frequently observed. A posteriori analysis reveals 50~--~70% alignment with Bayesian optimization sampling strategies. All AUTO simulations ran within 100 iterations (about 10 hours), with estimated costs of 15~--~159 per run for proprietary models. Furthermore, AUTO is built entirely on open-source LLMs and libraries, demonstrating affordability and data privacy. Given AUTO's generizability and flexibility, future work will explore domains beyond GPUs and supercomputing.