Large language models steady networked control systems with slow supervision
Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems
Artificial Intelligence
Summary
Some computer systems that control physical devices or multiple agents need to be very reliable and stable. The paper's authors review how large language models (LLMs), which usually take time to respond and can be unpredictable, can still be included in these systems safely. They explain that if the LLM acts slowly to set high-level goals while a faster, certified system handles immediate control, stability can be maintained. They also compare typical LLM behaviors to known network control problems and say more research is needed to guarantee safety formally.
What this means in practice
- •For control systems engineers: Design control loops that include large language models without losing physical stability by treating LLM latency and errors as network delays and disturbances.
- •For robotics integration teams: Incorporate LLMs for setting high-level goals in multi-robot systems while using fast inner loops to maintain real-time safety.
A survey. It maps existing work.
Authors
Haiping Du, Linping Chan
Abstract
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.