This paper mainly addresses the heterogeneous fleet capacitated vehicle routing problem with two-dimensional loading constrains (2L-HFCVRP). The 2L-HFCVRP is a combination of two NP-hard problems and has a wide range of applications in transportation and logistics fields. In this paper, we propose a hybrid swarm algorithm, which is a combination of Artificial Bee Colony (ABC) algorithm and Artificial Immune System (AIS) algorithm, to solve the 2L-HFCVRP. The proposed algorithm is allowed to search infeasible solutions and several efficient strategies are developed to escape from local optima. The extensive computational results on several well-known benchmark data sets verify the effectiveness of the proposed algorithm. The proposed algorithm is shown to outperform the best algorithms in the literature for 2L-HFCVRP instances. Published by Elsevier B.V.