This paper describes a novel method of achieving load balancing in telecommunications networks. A simulated network models a typical distribution of calls between arbitrary nodes; nodes carrying an excess of traffic can become congested, causing calls to fail. In addition to calls, the network also supports a population of simple mobile agents with behaviours modelled on the trail laying abilities of ants. The agents move across the network between arbitrary pairs of nodes, selecting their path at each intermediate node according to the distribution of simulated pheromones at each node. As they move they deposit simulated pheromones as a function of their distance from their source node, and the congestion encountered on their journey. Calls between nodes are routed as a function of the pheromone distributions at each intermediate node. The performance of the network is measured by the proportion of calls which fail. The results are compared with those achieved by using fixed shorte...