Intelligent learning systems (ILSs) have evolved in the last few years basically because of influences received from multi-agent architectures (MAs). Conflict resolution among agents has been a very important problem for multi-agent systems, with specific features in the case of ILSs. The literature shows that ILSs with cognitive or pedagogical agents are prone to arbitration methods, where as ILSs with reactive agents are much in favor of control mechanisms. For these kind of systems, different control types are proposed based on the different stimuli that these agents will receive. These stimuli are aspects to be evaluated during the teaching/learning process such as: (1) error analysis, (2) learning styles, (3) analogies, (4) social aspects, etc. The paper reviews several ILSs, related to our work; different control mechanisms are proposed to solve the agents' intervention conflicts. Finally, the use of several mechanisms is exemplified by the results of a specific ILS. (Contains 4 tables and 3 figures.)