Automated Design Optimization via Strategic Search with Large Language Models
By: Anthony Carreon, Vansh Sharma, Venkat Raman
Potential Business Impact:
Helps computers design better code faster and cheaper.
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.
Similar Papers
Automated Algorithm Design for Auto-Tuning Optimizers
Machine Learning (CS)
Makes computer programs run much faster automatically.
LLM for Large-Scale Optimization Model Auto-Formulation: A Lightweight Few-Shot Learning Approach
Artificial Intelligence
Helps computers build smart plans faster.
Fully Automated Generation of Combinatorial Optimisation Systems Using Large Language Models
Software Engineering
Computers automatically build smart helpers for businesses.