The topic of this work is the problem solving issue using simple interacting entities. The main difficulty of such a method stems from the paradox between the complexity of the problem, on one side, and the conceptual and functional simplicity of the entities on the other side. In order to overcome this paradox, we propose a method based on a reactive multi-agent system. This solving principle points out the importance of the interaction, and their integration in the agents' environment. As for the use of such a system to solve a real problem, the environment plays a key role. First, it represents the problem to solve on both topological and dynamical points of view. Second, it takes action into the solving process by determining the collective evolution of the agents thanks to the implementation of a system's Physics. In this paper, we describe the solving model we propose and its validation through experimental test performed both on simulation and with real targets.