Aug 2026· TH Wildau Engineering and Natural Sciences Proceedings· Vol 3· 0 citations· 14 references
TL;DR
An AI-based approach to supporting control rooms in large-scale infrastructures is presented that consolidates knowledge from operating manuals, experiential expertise, and real-time data, and makes it accessible through a natural language interface.
Abstract
An AI-based approach to supporting control rooms in large-scale infrastructures is presented. Distributed data sources, unclear documentation, and complex system depen-dencies make rapid and reliable decision-making difficult in such environments. The developed assistance system consolidates knowledge from operating manuals, experiential expertise, and real-time data, and makes it accessible through a natural language interface. Technically, the system is based on a locally operated multi-agent architecture that integrates data from moni-toring and control software. A verifiable workflow with fixed feedback loops ensures that inputs and outputs remain traceable and stable. This makes it possible to translate probabilistic mod-els into comprehensible and reproducible action steps—an essential aspect for deployment in safety-critical environments. The development and testing take place in scientific facilities being established at DESY Zeuthen. The paper describes initial results, challenges related to data quality and integration, and the potential contributions of the approach to resilient, transparent, and sustainable AI support systems for control rooms.
It is argued that agentic AI should be approached as a socio-technical design problem, where interfaces, oversight mechanisms, and evaluation practices are as critical as algorithms.
Timothy Merritt, Alejandro Jarabo-Peñas, Juan Bravo-Arrabal et al.· 0 citations
Abstract. Agent-Based Modelling and Simulation (ABMS) is widely used in System-of-Systems (SoS) studies to represent constituent systems operating in dynamic environments. However, the absence of standardised agent architectures hinders scalability, behaviour traceability, and comparative evaluation of emergence, coordination, and operational performance. This work introduces a modular agent design based on Observe–Orient–Decide–Act (OODA) loops as a framework for SoS simulations, enabling transparent information flow and Artificial Intelligence (AI) integration at the decision layer. A wildfire suppression scenario is used for the study, modelling firefighting crews, aircraft, helicopters, bulldozers, and an incident commander as OODA-driven agents. Results show that OODA-based agents exhibit coherent and traceable team behaviours, adaptive task switching, and communication-driven coordination, supporting the study of emergence and interoperability in SoS operations. The Decision stage is designed for future improvements in the form of learning-based AI and Large Language Models to enhance autonomy and operational fidelity.
J. Lovaco· Materials Research Proceedin...· 0 citations
The proposed framework for implementing an AI decision-maker and automation requires an IT specialist to implement it properly, and the AI model’s accuracy depends on the amount of input data.
A systematic literature review of technical approaches, including agent architecture, perception, memory, reasoning and planning, action space, orchestration, and self-improvement, reveals a field that has built agents able to act but not yet agents whose authority is bounded or whose behavior is auditable.
Jing-Jing Nie, Jiawei Guo, Krishna Meda et al.· 0 citations
A solver-grounded design principle is presented: a numerical result is reported only when it originates from a trusted tool and passes explicit verification, and a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency is proposed.
Daniel Rojas, Abdulwahab Albassam, Aidan G. Leung et al.· arXiv.org· 0 citations
