Abstract. In this work standard lattice cellular automata and random Boolean networks are extended to a wider class of generalized automata networks having any graph topology as a support. Dynamical, computational, and problem solving capabilities oftheseautomatanetworksarethendiscussedthroughselected examples, and put into perspective with respect to current and future research. 1

We investigate the performances of collective task-solving capabilities and the robustness of complex networks of automata using the density and synchronization problems as typical cases. We show by computer simulations that evolved Watts–Strogatz smallworld networks have superior performance with respect to several kinds of scale-free graphs. In addition, we show that Watts–Strogatz networks are as robust in the face of random perturbations, both transient and permanent, as configuration scale-free networks, while being widely superior to Barabási–Albert networks. This result differs from information diffusion on scale-free networks, where random faults are highly tolerated by similar topologies.