A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving
arXiv:2509.08269v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly integrated with evolutionary computation to support optimization tasks. This survey primarily focuses on evolutionary optimization, i.e., optimization based on evolutionary computation. For brevity, we use the term optimization throughout to denote this scope. However, existing surveys typically examine isolated roles of LLMs and do not provide a unified view that connects optimization modeling with optimization solving. To address this gap, we systematically review recent developments throu
The increasing integration of LLMs with evolutionary computation is reaching a point where a unified understanding of their combined potential for optimization tasks is necessary.
This survey provides a comprehensive view of how LLMs can transform optimization, bridging the gap between modeling and solving, which is crucial for advancing AI's practical applications.
The systematic review offers a consolidated framework for understanding LLM-driven evolutionary optimization, highlighting new methodologies for complex problem-solving in various domains.
- · AI developers
- · Optimization researchers
- · Industries with complex optimization problems
- · Traditional optimization methods
More efficient and sophisticated AI-driven optimization solutions will emerge across various industries.
The ability to solve previously intractable optimization problems will accelerate innovation in fields like materials science, logistics, and drug discovery.
This could lead to new economic efficiencies and competitive advantages for entities effectively leveraging these advanced optimization capabilities.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI