Improving LLM-based Global Optimization with Search Space Partitioning

Andrej Schwanke, Lyubomir Ivanov, David Salinas, Fabio Ferreira, Aaron Klein, Frank Hutter, Arber Zela

Keywords: global optimization, LLMs, blackbox optimization, multi-armed bandits

TL;DR: HOLLM is a global optimization algorithm that adaptively partitions the search space and generates promising candidate solutions in them with LLMs.

Abstract: Large Language Models (LLMs) have recently emerged as effective surrogate models and candidate generators within global optimization frameworks for expensive blackbox functions. Despite promising results, LLM-based methods often struggle in high-dimensional search spaces or when lacking domain-specific priors, leading to sparse or uninformative suggestions. To overcome these limitations, we propose HOLLM, a novel global optimization algorithm that enhances LLM-driven sampling by partitioning the search space into promising subregions. Each subregion acts as a ``meta-arm'' selected via a bandit-inspired scoring mechanism that effectively balances exploration and exploitation. Within each selected subregion, an LLM then proposes high-quality candidate points, without any explicit domain knowledge. Empirical evaluation on standard optimization benchmarks shows that HOLLM consistently matches or surpasses leading global optimization methods, while substantially outperforming global LLM-based sampling strategies.

Primary Area: optimization

Submission Number: 7956