Cognitive systems must reason with large bodies of general knowledge to perform complex tasks in the real world. However, due to the intractability of reasoning in large, expressive knowledge bases (KBs), many AI systems have limited reasoning capabilities. Successful cognitive systems have used a variety of machine learning and axiom selection methods to improve inference. In this paper, we describe a search heuristic that uses a Monte-Carlo simulation technique to choose inference steps. We test the efficacy of this approach on a very large and expressive KB, Cyc. Experimental results on hundreds of queries show that this method is highly effective in reducing inference time and improving question-answering (Q/A) performance.