There exists a number of problems which involve multiple sources of knowledge and, thereby, can best be addressed using a multi-agent system (MAS) --a computational system composed of several interacting agents which cooperate with one another to solve complex tasks. Furthermore, the deployment of multi-agent systems permits to benefit from a number of advantages --such as parallelism, robustness and scalability-- that a single agent working isolatedly can not offer itself. Coordinating the activities of the several agents composing a MAS is essential in order to guarantee the proper workings of a MAS itself and benefit from such advantages.
Currently, we are partners of the SMASH project, a collective, joint effort involving several research institutions that addresses the construction of multi-agent systems that help solve problems of distributed nature in hospital services. The development of such multi-agent systems requires the deployment of (highly flexible) communication and coordination mechanisms to integrate a set of heterogeneous agents --agents developed by different people for different purposes and in different languages-- within a common setting. Instead of letting agents deal themselves with such issues, our proposal opts for introducing an autonomous software agent that we call interagent which manages (intermediates) the communication and coordination between the agent it is attached to and the agent society wherein it is situated.