Bridging Knowledge Gaps in Smart City Intelligence Using Federated Explainable Agentic AI

Increasingly, urban smart city systems depend on data-driven intelligence for making informed decisions related to transportation, energy, and public administration. Nevertheless, the current strategies still lack cohesion. In this study, we introduce a Federated Explainable Agentic AI (FEA-AI)-based framework for smart cities that combines decentralized federated learning, explainable decision making, and agent-based autonomous reasoning in order to facilitate private local data analysis, interpretation of results, and flexible decision making in dispersed environments. The newly proposed framework has a lot of positive factors compared to centralized methods. The framework's value lies in the provision of certain foundations for smart urban management intelligence.