We investigate ant-colony-inspired foraging strategies for enhancing the efficiency of a swarm of artificial agents engaged in a search-and-retrieval application. First, we extend a mathematical model of ant foraging to account for the evolution of the information collected during search-and-retrieval over time. We then use the extended model to numerically investigate the efficiency of search-and-retrieval under the two distinct cases of non-depleting information and depleting information at the sources. In the former case, we obtain optimal ranges of parameter values of the ant foraging model that enhance efficiency. In the latter case, we find that appropriately designed deposition functions in the model can induce self-organization in the swarm and therefore prioritize the collection of quickly depleting information. The ability to prioritize is highly desirable in a swarm for search-and-retrieval applications and, to our knowledge, induced emergent behavior resulting in prioritization capabilities has not been reported in swarms inspired by ant foraging. The results are expected to be broadly significant for swarm robotics as well as in applications such as the Travelling Salesman Problem (TSP) with time-varying profit.