We evaluate the state of the art of solvers for hard argumentation problems—the enumeration of preferred and stable extensions—to envisage future trends based on evidence collected as part of an extensive empirical evaluation. In the last international competition on computational models of argumentation a general impression was that reduction-based systems (either SAT-based or ASP-based) are the most efficient.
Our investigation shows that this impression is not true in full generality and suggests the areas where the relatively under-developed non reduction-based systems should focus more to improve their performance. Moreover, it also highlights that the state-of-the-art solvers are very complementary and can be successfully combined in portfolios: our best per-instance portfolio is 51% (resp. 53%) faster than the best single solver for enumerating preferred (resp. stable) extensions.