Self-organizing multi-agent systems (MAS) use different mechanisms to mimic the adaptation exhibited by complex systems situated in unpredictable and dynamic environments. These mechanisms allow a collection of agents to spontaneously adapt their behavior towards an optimal organization. This paper presents a self-organization approach that exploits several selforganizing principles through an agent adaptive architecture and a reinforcement mechanism. This mechanism was designed and implemented using the INGENIAS methodology. Categories and Subject Descriptors I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence