Measuring Architectural Efficiency in Agentic Manufacturing: The Iaea Index and its Application in the MECA Framework

The transition toward autonomous manufacturing in Industry 5.0 necessitates a paradigm shift from qualitative descriptions of “intelligence” to quantitative measures of architectural robustness. This paper addresses the current lack of holistic metrics for vertically integrated agentic systems by formalizing the Agentic Architectural Efficiency Index (I_AEA). This novel mathematical index evaluates the synergy between cognitive reasoning and physical determinism by integrating three critical dimensions: causal traceability, vertical completeness, and cumulative latency. To validate this metric, we implement the Modular Explainable Contextual Agentic (MECA) framework, an architecture designed to bridge high-level AI intent with real-time robotic execution. The framework’s core novelty lies in the coupling of Timed Petri Nets for formal safety verification and ROS2/DDS for deterministic communication. Preliminary results from a numerical case study in a robotic polishing cell demonstrate that the MECA framework achieves a tenfold increase in architectural efficiency (I_AEA ≈ 0.65) compared to baseline models (I_AEA ≈ 0.06). By providing a verifiable standard for auditing agentic systems, these findings establish a rigorous path toward autonomous manufacturing where explainability and formal supervision foster operational resilience.