Abstract. In multi-agents systems, incompleteness, due to either communication failure or response delay, is a major problem to handle. To face incompleteness, frameworks for speculative computation were proposed (see [5,6,4]). The idea developed in such frameworks is to allow the asking agent, while waiting for slave agents to reply, to reason using default belief until replies are sent. In [6] in particular, a framework is proposed, that allows an agent not only to perform speculative computation but also to accept iterative answer revision, in the case of yes/no questions. In this paper, we present an extension of the framework in the case of more general types of questions using constraint logic programming (CLP).