智能体
arxiv.org ·
GA-Agent：用大语言模型作为进化控制器合成的超参数优化器
该 arXiv 预印本提出 GA-Agent，将 PID 控制器调参解耦为两层：底层用标准遗传算法优化增益，元层由 LLM 代理观察已完成的 GA 运行、诊断与用户控制目标的差距并更新 GA 配置（种群规模、代数预算、增益边界、适应度权重）。在直流电机、倒立摆、飞机俯仰、自主水下航行器等 8 个控制案例上，作者报告全部成功，解质量与样本效率优于固定超参数的常规 GA，与 Cascade-GA 基线相当或更优，函数评估减少 1 至 2 个数量级，通常 1 至 3 次优化尝试即收敛；敏感性分析显示对 LLM 后端和记忆配置稳健，2-3 大小的紧凑记忆缓冲配合低成本模型（DeepSeek-V4-Flash，约每次运行 0.002 美元）表现更佳。
AI推荐理由 arXiv 预印本，摘要信息密度较高，给出了具体方法（LLM 作为 GA 元层控制器）、8 个控制案例、函数评估减少 1-2 个数量级、单次约 0.002 美元等可核查细节，属于 LLM 用于自动化超参数优化的新方向。局限在于仅为预印本、未提供同行评审或代码链接，'100% 成功'等结论需独立复现验证，且应用场景偏控制工程，对通用 AI 从业者价值有限。
72
正文
Electrical Engineering and Systems Science > Systems and Control
arXiv:2609.27725 (eess)
[Submitted on 23 Sep 2026]
Title:GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis
Authors:Mohammad Narimani, Seyyed Ali Emami
View a PDF of the paper titled GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis, by Mohammad Narimani and 1 other authors
View PDF
HTML (experimental)
Abstract: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.
Subjects:
Systems and Control (eess.SY)
Cite as:
arXiv:2609.27725 [eess.SY]
(or
arXiv:2609.27725v1 [eess.SY] for this version)
https://doi.org/10.48550/arXiv.2609.27725
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Seyyed Ali Emami [view email]
[v1]
Wed, 23 Sep 2026 11:40:12 UTC (1,114 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis, by Mohammad Narimani and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
eess.SY
new
|
recent
| 2026-09
Change to browse by:
cs
cs.SY
eess
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)