用控制理论设计多智能体系统，让大模型在工业控制中安全可审计。
A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process Control
- 基于先进调节控制理论，将每个控制回路拆分为专用大模型代理。
- 通过确定性调度器处理冲突，即使大模型输出异常也能保证安全。
- 在奶牛棚通风场景验证，生成带解释的可审计控制轨迹。
现有研究显示，大语言模型（LLMs）在通用任务中表现良好，但在特定领域任务中表现不佳，原因在于难以向通用模型提供窄范围上下文，也难以限定其任务边界。本文提出一种基于先进调节控制（ARC）理论的多智能体重构方法，该理论将系统分解为具有明确控制范围的单元，每个单元负责一个受控变量，并通过结构化优先级解决冲突：使用最小/最大选择网络实现受控变量间的切换，采用分程（并联）逻辑实现操作变量间的切换。本文将每个控制回路映射为一个具备控制理论上下文（受控变量、设定值、链路优先级、选择类型）的专用大模型操作代理，整个链路的交互逻辑（最小/最大选择器、优先路径）由单一调度代理封装。测试了两种调度器变体：确定性规则链和基于Claude的低速大模型调度器。控制原则限制每个代理的任务范围，并指导如何处理其局限性。多智能体系统继承了ARC链的安全特性：所有约束冲突均由调度器确定性解决，与大模型输出无关。在4天混合季节的奶牛棚通风场景中，运行于24GB消费级GPU上的Qwen 2.5 7B Instruct操作代理以5分钟采样频率离线执行，生成可审计的控制轨迹，并附带操作代理的语音解释，支持控制策略日志记录。
原文摘要 · Abstract (English)
Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason is the difficulty of supplying narrow context to a general-purpose model and of bounding the task it is asked to perform. It is possible to hypothesise that a multi-agent reformulation under process-control principles offers a route to address those points, since control theory provides a discipline of decomposing a system into elements of contained scope, each defending one controlled variable, with conflicts resolved by structural priority: MIN/MAX selector networks for CV-CV switching and split-range (split-parallel) logic for MV-MV switching. The present work proposes such a reformulation, derived from Advanced Regulatory Control (ARC) theory. Each feedback loop in the ARC chain is mapped to one specialised LLM operator agent carrying the loop's control-theoretic context (controlled variable, setpoint, chain priority, selector kind). The chain's interaction logic (MIN/MAX selectors, override paths) is encapsulated as a single orchestrator agent. Two orchestrator variants are tested: a deterministic rule chain, and a Claude-based LLM orchestrator at a slower tier. The control principles limit each agent's task and inform how its limitations are handled. The multi-agent system inherits the safety property of the ARC chain: every constraint conflict is resolved deterministically by the orchestrator, regardless of the LLM output. Evaluated on a dairy-barn ventilation case over a 4-day mixed-season scenario, Qwen 2.5 7B Instruct operator agents running offline on a 24 GB consumer GPU at a 5-minute cadence produce auditable trajectories, each paired with an operator-voice rationale that supports a control campaign logbook.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。