发表机构
University of Wollongong（伍伦贡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述提出统一框架，将LLM作为慢速监督者纳入NCS、CPS和CNS控制回路，映射经典网络化挑战，并指出形式化稳定性证明缺失是核心开放问题。
AI 中文摘要
现代网络化控制系统（NCSs）、信息物理系统（CPSs）和复杂多智能体网络系统（CNSs）日益依赖大语言模型（LLMs）进行高层决策。然而，LLMs的缓慢、随机特性与这些物理系统所需的严格稳定性和安全性保证直接冲突。本综述对LLMs如何在不妨碍闭环保证的前提下被纳入NCS、CPS和CNS的控制回路进行了统一分析。我们围绕一个核心原则进行组织：LLM作为慢速监督者，调整高层目标和约束，而快速、经过认证的内环则维持物理稳定性。在此框架下，LLM集成直接映射到经典网络化控制挑战，其中推理延迟充当时延，API故障充当数据包丢失，分词充当量化，幻觉充当有界扰动。我们评估了这三个领域的最新进展，强调不断增长的模型能力常常伴随着形式化安全保证的下降。最后，我们提出了具体的未来研究方向，指出普遍缺乏形式化稳定性证明是该领域的核心开放问题。
英文摘要
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.
