… markable success in tackling complex combinatorial optimization problems. However, EAs
often … In this work, we present the first study on large language models (LLMs) as evolutionary …

… -based Prompt Optimization. Our findings reveal that the LLM optimizers struggle to identify
… Furthermore, even when the reflection is semantically valid, the LLM optimizers often fail to …

… suitable for discrete prompt optimization. Sequences of phrases … language processing and
the exceptional optimization … operators and EAs guide the optimization process to retain the …

… the optimization capabilities of Large Language Models. To achieve this, we employ the
goal metric, which serves as a quantitative measure of the extent to which the optimization …

… optimization problem is difficult to solve as the set of feasible points is sparse, the space is
discrete, and the language models … , we introduce a discrete optimization algorithm, ARCA, …

… large language models (LLMs) to make decisions during hyperparameter optimization (HPO). …
like random search and Bayesian optimization on standard benchmarks. Furthermore, we …

… Bayesian optimization (BO) is a powerful approach for optimizing complex and … of large
language models (LLM) within BO. At a high level, we frame the BO problem in natural language …

… of optimization tools and techniques. We introduce OptiMUS, a Large Language Model (LLM)-…
from their natural language descriptions. OptiMUS is capable of developing mathematical …

… Optimization problems are … , a Large Language Model (LLM)-based agent designed to
formulate and solve (mixed integer) linear programming problems from their natural language …

… leveraging Large Language Models (LLMs) to automate hyperparameter optimization across
diverse … This human-like optimization process largely reduces the number of required trials, …