Architectures necessary for fusion of decisions from sensors with limited decision capabilities, such as binary decision sensors operating in multidecision problem environments, are conceived and analyzed. The analysis is carried out from the perspective of efficiency of operations, as defined by the problem environment and its constraints. It takes into account the a priori probabilities or likelihoods of the different decision choices in the environment in developing estimates of the processing demands corresponding to these architectures. The analysis also brings out the feasibility of designing the architecture to be adaptive to take full advantage of the information about the relative likelihoods of the different decision choices facing the fusion processor as the information evolves during the operational phase. Architectures that are insensitive to the relative probabilities of the alternative decision choices are also brought out under this analysis. The relative merits of these alternatives, their preferred domains in the class a priori probability space, and their relevance to different application environments are discussed to identify the natural domains of application of these architectures.