Large-scale crowd phenomena are complex to model as the behaviour of pedestrians needs to be described at both strategic, tactical, and operational levels and is impacted by the density of the crowd. Microscopic models manage to mimic the dynamics at low densities, whereas mesoscopic models achieve better performances in dense situations. This paper proposes and evaluates a novel agent-based architecture to enable agents to dynamically change their operational model based on local density. The ability to combine microscopic and mesoscopic models for multi-scale simulation is studied through a use case of pedestrians at the Festival of Lights, Lyon, France. Simulation results are compared to different models in terms of density map, pedestrian outflow, and computation time. The results demonstrate that our agent-based architecture can effectively simulate pedestrians in diverse-density situations, providing flexibility for incorporating various models, and enhancing runtime performance while achieving comparable pedestrian outflow results to alternative models.