Heuristic functions are used to guide the search of algorithms such A* while solving state-space search problems. In this talk I will discuss several strategies for selecting subsets of heuristics to guide the A* search. We apply our subset selection algorithms to domain-independent planning. That is, to problems specified in a language such as PDDL for which no prior knowledge is provided. I will show how our algorithms are able to improve the state of the art in domain-independent planning.