Increasing customer demands and variability in today’s logistics networks force fleet operators to become more reliable and flexible in their operations. As modern-day fleets are well equipped with wireless sensing, processing, and communication devices, fleet operators could proactively respond to dynamic events. However, the use of real-time sensor data to achieve re-optimization is scarce. This observation raises the question of how logistics operators should incorporate the emerging track-and-trace services into their dynamic planning activities. In this paper, we propose a reference architecture that relies on both the Internet of Things and the Smart Logistics paradigms, and aims at enhancing the resilience of logistics networks. Since the decision of when to reschedule the network’s configurations remains nontrivial, we propose a hierarchical set of disruption handling systems to facilitate the trade-off between decision quality and response time. In our design, autonomous logistics agents can quickly anticipate on minor changes in their surroundings, while more severe disruptions require both more data and computational power in higher-level processing nodes (e.g., fog/cloud computing, machine learning, optimization algorithms). We illustrate the need of our architecture in the context of the dynamic vehicle routing problem.