Swarm intelligence is the collective-level, problem-solving behavior of groups of relatively simple agents. Local interactions among agents, either direct or indirect through the environment, are fundamental for the emergence of swarm intelligence; however, there is a class of interactions, referred to as interference, that actually blocks or hinders the agents' goal-seeking behavior.

Traditional approaches deal with interference by complexifying the behavior and/or the characteristics of the agents that comprise a swarm intelligence system, limiting its scalability and increasing the difficulty of the design task. A framework, called incremental social learning (ISL), has been proposed to tackle the interference problem in swarm intelligence systems. Through the use of ISL, interference can be reduced without changing the original design of the system's constituent agents. The observable effect of ISL on a swarm intelligence system is an improvement of the system's performance. In this talk, the ISL framework will be described in detail. Furthermore, three instantiations of the framework, which demonstrate the framework's effectiveness, will also be presented. The swarm intelligence systems used as case studies are the particle swarm optimization algorithm, ant colony optimization algorithm for continuous domains, and the artificial bee colony optimization algorithm.