Safety
Automated Design Optimization via Strategic Search with Large Language Models
arXiv:2511.22651v2 Announce Type: replace-cross Abstract: Optimization methods have long advanced many fields, yet they struggle when faced with design problems where the search space and design param
arXiv:2511.22651v2 Announce Type: replace-cross Abstract: 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 1.74imes for problem sizes up to 10^5 cells. For matrix multiplication, AUTO achieves up to 94% of cuBLAS double-precision performance. For KernelBench, we achieve speedups of up to 118imes 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.
Related
- PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
- Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models
- PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models
Source: arXiv cs.AI | 2026-08-14