Transfer learning is the ability of an agent to apply knowledge learned in previous tasks to new problems or domains. We approach this problem by focusing on model formulation, i.e., how to move from the unruly, broad set of concepts used in everyday life to a concise, formal vocabulary of abstractions that can be used effectively for problem solving. This paper describes how the Companions cognitive architecture uses analogical model formulation to learn to solve AP Physics problems. Our system starts with some basic mathematical skills, a broad common sense ontology, and some qualitative mechanics, but no equations. Our system uses worked solutions to learn how to use equations and modeling assumptions to solve AP Physics problems. We show that this process of analogical model formulation can facilitate learning over a range of types of transfer, in an experiment administered by the Educational Testing Service.