发表机构
Sharif University of Technology（谢里夫理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GA-Agent利用大型语言模型作为元级超参数优化器，动态配置遗传算法以合成PID控制器，在八个控制基准上实现100%成功率，并将函数评估次数减少一至两个数量级。
AI 中文摘要
调整PID控制器以满足相互竞争的目标——低跟踪误差、快速稳定、有限超调量和适度的控制力度——是劳动密集型的，并且需要专业知识。遗传算法（GAs）提供了针对加权适应度函数的控制器增益的无梯度优化，但其成功取决于元层面的选择：种群大小、世代预算、增益边界和适应度权重。这些通常通过手动试错或成本高昂的双层优化来设定，暴露了一种矛盾：遗传算法擅长密集数值搜索，但配置它们需要高层级、上下文相关的语义推理。我们提出了GA-Agent，它将这两种模式解耦。一个标准遗传算法处理低层级的PID增益优化。一个大型语言模型（LLM）代理在元层面运作：它观察已完成的遗传算法运行，诊断与用户控制目标之间的差距，并提出更新的遗传算法配置。该架构使用结构化记忆、定量目标转换、资源感知终止和基于结果的路径选择。我们在八个具有不同动态特性的控制案例研究（直流电机、倒立摆、飞机俯仰、自主水下航行器等）上评估了GA-Agent。GA-Agent在所有基准上实现了100%的成功率，在解质量和样本效率方面优于具有固定超参数的常规遗传算法。它匹配或超越了级联遗传算法基线，同时将函数评估次数减少了一到两个数量级，通常在一次到三次优化尝试中收敛。敏感性分析显示其在不同LLM骨干网络和记忆配置下具有鲁棒性。一个紧凑的记忆缓冲区（大小为2-3）和成本效益高的模型（DeepSeek-V4-Flash，每次运行约0.002美元）实现了卓越的性能。
英文摘要
Tuning PID controllers to satisfy competing objectives - low tracking error, fast settling, limited overshoot, and moderate control effort - is labor-intensive and requires expertise. Genetic algorithms (GAs) offer gradient-free optimization of controller gains against a weighted fitness function, but success depends on meta-level choices: population size, generation budget, gain bounds, and fitness weights. These are usually set by manual trial-and-error or costly bilevel optimization, exposing a tension: GAs excel at dense numerical search, but configuring them needs high-level, context-dependent semantic reasoning. We propose GA-Agent, which decouples these modes. A standard GA handles low-level PID gain optimization. A large language model (LLM) agent operates at the meta-level: it observes completed GA runs, diagnoses gaps versus user control objectives, and proposes updated GA configurations. The architecture uses structured memory, quantitative goal translation, resource-aware termination, and outcome-driven routing. We evaluate GA-Agent on eight control case studies with diverse dynamics (DC motor, inverted pendulum, aircraft pitch, autonomous underwater vehicle, and others). GA-Agent achieves 100% success on all benchmarks, outperforming a Regular GA with fixed hyperparameters in solution quality and sample efficiency. It matches or surpasses a Cascade-GA baseline while reducing function evaluations by one to two orders of magnitude, typically converging in one to three optimization attempts. Sensitivity analysis shows robustness across LLM backbones and memory configurations. A compact memory buffer (size 2-3) and cost-effective models (DeepSeek-V4-Flash at about $0.002 per run) achieve superior performance.
