TL;DR
A hierarchical intelligent optimization framework is proposed and Large Language Models (LLMs) are introduced as strategy optimizers, thereby proposing the LLM-HSO algorithm, which leverages the contextual understanding and code generation capabilities of LLMs to perform evaluation and strategy reconstruction during the evolutionary process.
Experimental results demonstrate that LLMDE achieves competitive performance on the benchmark suite while continuously generating high-quality solutions for complex constrained optimization tasks, and successfully demonstrate the viability of embedding LLMs within metaheuristics, paving a promising path toward the desi...
Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated parameters. Existing hybrid evolutionary algorithms typically rely on static architectures or fixed switching rules, resulting in disjointed search phases. To address th...
This paper characterize in-context evolutionary stagnation and analytically propose the Improvement Chain proposition, showing how learning successive self-generated algorithms can locally increase the likelihood of neighboring algorithms.
Learning-based hyper-heuristics for combinatorial optimization select from among low-level operators or tune the parameters of a single metaheuristic. However, online selection among complete population-based metaheuristics that share one evolving population and its joint configuration through a common action space hav...
Dynamic resource configuration in regional industrial clusters is pivotal for unlocking their collective efficiency and ensuring resilience in cyber-physical production systems. However, static optimization methods suffer from a fundamental mismatch against volatile industrial rhythms, lacking the situational awareness...
This work shows empirically that solver-integrated reasoning, exact combinatorial algorithm, and heuristic search exhibit complementary strengths across different problem structures and scales, and introduces Strategy-Diverse Reinforcement Learning (SDRL), which trains LLMs as adaptive optimization meta-solvers.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
