{"ID":5439498,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T19:54:01.969788673Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30877","arxiv_id":"2606.30877","title":"A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process Control","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2606.30877","url_pdf":"https://arxiv.org/pdf/2606.30877v1","authors":"[\"Idelfonso B. R. Nogueira\",\"Sigurd Skogestad\"]","published":"2026-06-29T20:07:47Z","proceeding":"eess.SY","tasks":"[\"eess.SY\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}