Automated Design Optimization via Strategic Search with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carreon, Anthony, Sharma, Vansh, Raman, Venkat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908679734820864
author Carreon, Anthony
Sharma, Vansh
Raman, Venkat
author_facet Carreon, Anthony
Sharma, Vansh
Raman, Venkat
contents Traditional optimization methods excel in well-defined search spaces but struggle with design problems where transformations 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 introduce AUTO, an LLM agent framework that treats design optimization as a gradient-free search problem guided by strategic LLM reasoning. The framework employs two collaborative agents: a Strategist that selects between exploration and exploitation strategies, and an Implementor that executes detailed designs. Applied to GPU code optimization -- a domain critical to fields from machine learning to scientific computing -- AUTO generates solutions competitive with expert implementations for chemical kinetics integration and dense matrix multiplication. The framework achieves 50-70% search efficiency relative to Bayesian optimization methodologies. It completes optimizations in approximately 8 hours at an estimated cost of up to \$159 per run, compared to an estimated cost of up to \$480 with median-wage software developers. These findings open the door to automating design optimization in ill-defined search spaces with limited prior information.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automated Design Optimization via Strategic Search with Large Language Models
Carreon, Anthony
Sharma, Vansh
Raman, Venkat
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Multiagent Systems
Traditional optimization methods excel in well-defined search spaces but struggle with design problems where transformations 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 introduce AUTO, an LLM agent framework that treats design optimization as a gradient-free search problem guided by strategic LLM reasoning. The framework employs two collaborative agents: a Strategist that selects between exploration and exploitation strategies, and an Implementor that executes detailed designs. Applied to GPU code optimization -- a domain critical to fields from machine learning to scientific computing -- AUTO generates solutions competitive with expert implementations for chemical kinetics integration and dense matrix multiplication. The framework achieves 50-70% search efficiency relative to Bayesian optimization methodologies. It completes optimizations in approximately 8 hours at an estimated cost of up to \$159 per run, compared to an estimated cost of up to \$480 with median-wage software developers. These findings open the door to automating design optimization in ill-defined search spaces with limited prior information.
title Automated Design Optimization via Strategic Search with Large Language Models
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Multiagent Systems
url https://arxiv.org/abs/2511.22651