The challenge we address in this work is the control of complex systems. We consider techno-social systems. Techno-social systems and complex systems share some characteristics like big number of entities, autonomous entities, pre-existing systems, and multiple levels of organization. The solution to the control challenge we envisage is based on the multi-agent paradigm. The paradigm is well fit to deal with complex systems because it treats multiple levels of description at the same time. Our focus is on identifying what specific questions arise when using the multi-agent paradigm in the control of complex systems context. We present here a solution under the form of an equation-free control architecture based on multiagent model simulation. An example implementation of the architecture is presented. The implementation is done within the context of a collective phenomenon of a techno-social system the free-riding of peer-topeer file sharing networks. Preliminary results of the implementation demonstrate that the proposed architecture can control such a network. Our contribution is to identify key questions that rise when using the multi-agent paradigm in the context of control of complex systems, concerning the relationship between the model entities and the target system entities.