{"ID":2836075,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22651","arxiv_id":"2511.22651","title":"Automated Design Optimization via Strategic Search with Large Language Models","abstract":"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.","short_abstract":"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 thi...","url_abs":"https://arxiv.org/abs/2511.22651","url_pdf":"https://arxiv.org/pdf/2511.22651v1","authors":"[\"Anthony Carreon\",\"Vansh Sharma\",\"Venkat Raman\"]","published":"2025-11-27T17:42:05Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CE\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}