Metraipolis › archive › dc_d1bc211ecf97

Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems — arXiv:2609.16599

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16599
License (as archived)
CC0-1.0
Archived
2026-10-15T18:35:06.259Z
SHA-256 of the archived text
b4842ec5e76e42b4982dfc7f134d1abe52759d725a670eb885e754221e6af47e
Stable URL of this page
https://metraipolis.com/documento/dc_d1bc211ecf97

How to cite

Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems — arXiv:2609.16599 — arXiv (en), https://arxiv.org/abs/2609.16599 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1bc211ecf97 (Metraipolis archive dc_d1bc211ecf97, sha256 b4842ec5e76e42b4982dfc7f134d1abe52759d725a670eb885e754221e6af47e)
BibTeX
@misc{dcd1bc211ecf97,
  title = {Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems — arXiv:2609.16599},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16599},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1bc211ecf97; sha256 b4842ec5e76e42b4982dfc7f134d1abe52759d725a670eb885e754221e6af47e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16599. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large language models (LLMs) for high-level decision-making. However, the slow, stochastic nature of LLMs directly conflicts with the strict stability and safety guarantees required by these physical systems. This survey presents a unified analysis of how LLMs can be admitted into the control loop of NCS, CPS, and CNS without compromising closed-loop guarantees. We organize this around a core principle: the LLM operates as a slow supervisor adjusting high-level goals and constraints, while a fast, certified inner loop maintains physical stability. Under this framework, LLM integration maps directly to classical networked control challenges, where inference latency acts as delay, API failures as packet dropouts, tokenization as quantization, and hallucinations as bounded disturbances. We assess current developments across all these three domains, highlighting that rising model capabilities are frequently accompanied by a drop in formal safety assurances. Finally, we propose concrete future research directions, identifying the widespread lack of formal stability proofs as the field's central open problem.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Systems and Control (eess.SY) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.16599 — 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 2026-10-15T18:03:09.670Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).