Metraipolis › archive › dc_2e1defdcfe5f

GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis — arXiv:2609.27725

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27725
License (as archived)
CC0-1.0
Archived
2026-10-08T13:36:23.963Z
SHA-256 of the archived text
86f0bed2723dc0a72a17ae1864deaf57cd91d24d42acfb06a0a63f49dac48c9c
Stable URL of this page
https://metraipolis.com/documento/dc_2e1defdcfe5f

How to cite

GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis — arXiv:2609.27725 — arXiv (en), https://arxiv.org/abs/2609.27725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e1defdcfe5f (Metraipolis archive dc_2e1defdcfe5f, sha256 86f0bed2723dc0a72a17ae1864deaf57cd91d24d42acfb06a0a63f49dac48c9c)
BibTeX
@misc{dc2e1defdcfe5f,
  title = {GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis — arXiv:2609.27725},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e1defdcfe5f; sha256 86f0bed2723dc0a72a17ae1864deaf57cd91d24d42acfb06a0a63f49dac48c9c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-24 in eess.SY).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.27725 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:16:03.451Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).