LLM与进化计算双向融合，提升算法自动设计与优化能力
Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
- 用进化计算优化LLM的提示、超参和架构
- 用LLM改进进化算法的元启发式设计与算子控制
- 适合智能系统、自动化算法设计研究者参考
大型语言模型（LLMs）与进化计算（EC）正被结合用于支持自动化优化、算法设计与自适应决策。本文综述二者之间的双向交互机制，探讨如何利用其互补优势构建混合智能系统。首先分析进化计算如何通过提示优化、超参数调优和架构搜索增强基于LLM的系统。其次回顾语言模型如何通过支持元启发式设计、代理推理、自适应算子控制和启发式生成来改进进化计算。进一步讨论新兴的协同适应框架，其中LLM与EC通过迭代反馈循环交互。除总结近期进展外，本文还系统梳理了交互机制、应用模式与方法论挑战，包括计算成本、可复现性、可解释性、基准测试与泛化能力。最后提出开放问题与未来方向，旨在推动更鲁棒、透明、可扩展的LLM-EC系统发展。
原文摘要 · Abstract (English)
Large Language Models (LLMs) and Evolutionary Computation (EC) are increasingly being combined to support automated optimization, algorithm design, and adaptive decision-making. This survey reviews the bidirectional interaction between these two paradigms and examines how their complementary strengths can be leveraged in hybrid intelligent systems. First, we analyze how EC can enhance LLM-based systems through prompt optimization, hyperparameter tuning, and architecture search. Second, we review how LLMs can im- prove EC by supporting metaheuristic design, surrogate reasoning, adaptive operator control, and heuristic generation. We further discuss emerging co-adaptive frameworks in which LLMs and EC interact through iterative feedback loops. Beyond summarizing recent developments, the survey provides a structured perspec- tive on interaction mechanisms, application patterns, and methodological challenges, including computational cost, reproducibility, interpretability, benchmarking, and generalization. The paper concludes by outlining open research questions and future directions for developing more robust, transparent, and scalable LLM-EC systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。