We introduce a new framework for the study of reasoning. The Learning (in order) to Reason approach developed here views learning as an integral part of the inference process, and suggests that learning and reasoning should be studied together. The Learning to Reason framework combines the interfaces to the world used by known learning models with the reasoning task and a performance criterion suitable for it. In this framework, the intelligent agent is given access to its favorite learning interface, and is also given a grace period in with it can interact with this interface and construct a representation KB of the world <italic>W</italic>. The reasoning performance is measured only after this period, when the agent is presented with queries α from some query language, relevant to the world, and has to answer whether <italic>W</italic> implies α. The approach is meant to overcome the main computational difficulties in the traditional treatment of reasoning which stem from its separation from the “world”. Since the agent interacts with the world when construction its knowledge representation it can choose a representation that is useful for the task at hand. Moreover, we can now make explicit the dependence of the reasoning performance on the environment the agent interacts with. We show how previous results from learning theory and reasoning fit into this framwork and illustrate the usefulness of the Learning to Reason approach by exhibiting new results that are not possible in the traditional setting. First, we give Learning to Reason algorithms for classes of propositional languages for which there are no efficient reasoning algorithms, when represented as a traditional (formula-based) knowledge base. Second, we exhibit a Learning to Reason algorithm for a class of propositional languages that is not know to be learnable in the traditional sense.