The intelligent transformation of logistics plays a significant role in meeting the diverse needs of customers, improving operational efficiency, and reducing carbon emissions in logistics activities. Therefore, to achieve sustainable development, logistics enterprises need to face the decision-making problem of intelligent logistics transformation. In this paper, we construct a Stackelberg game model between a financially constrained logistics-service provider (LSP) and a well-funded logistics-service integrator (LSI) and discuss the impact of the wholesale price contract, the cost-sharing contract, the revenue-sharing contract, the two-part tariff contract, and the hybrid cost-sharing and revenue-sharing contract on the intelligence level of logistics services, the profits of supply-chain members, and the channel for logistics-service demand. We found that the cost-sharing contract and the revenue-sharing contract cannot achieve Pareto improvement in the profits of supply-chain members. In addition, the increase in bank-loan interest rates would seriously weaken the level of intelligence and market demand for the entire logistics service. However, when consumers do not have high requirements for the intelligence of logistics services, the two-part power–price contract can create a win–win situation for supply-chain members and increase market demand within a certain range; on the contrary, a hybrid contract of cost sharing and revenue sharing is the best choice. Moreover, in the process of contract design for the intelligent transformation of logistics services, it is necessary to pay attention to the influence of the price-sensitivity coefficient on decision-making.

Urban last-mile logistics increasingly faces small-batch, high-frequency, time-sensitive, and dispersed delivery. Multi-truck–multi-drone cooperation couples routing, drone sorties, battery operations, and synchronization, forming a complex system with multiple trade-offs. This study develops a unified framework to reduce composite operating costs under payload, endurance, synchronization, and soft time-window constraints. We propose a six-component cost model and a Q-learning-assisted hybrid genetic adaptive large neighborhood search algorithm (Q-HGALNS) that integrates delayed-assignment encoding, two-stage unified decoding, and state-dependent selection among 12 destroy–repair actions. Across 12 Solomon instance groups, Q-HGALNS achieved the lowest average cost and significantly outperformed GA, SA, and VNS in all cases, with overall relative cost reductions of 10.876%, 4.483%, and 16.869%. Ablation showed reductions of 0.972%, 1.064%, and 0.678% over NoQ, NoLS, and ALNS-AW. In a 100-point Shenzhen simulation, the lowest-cost feasible solution reduced total cost by 5.566% and the sum of vehicle completion times by 59.2 min versus the truck-only scenario. This study establishes a system-level coordination mechanism linking delayed service-mode decisions, unified decoding, and state-feedback search, enabling routing, sortie, battery, and temporal decisions to be jointly optimized. Q-HGALNS consistently achieves lower costs and supports executable planning and operational strategy design for urban last-mile delivery.