Fast and Efficient Partner Selection in Large Agents' Communities: When Categories Overcome Direct Experience

When it comes to collaboration within huge agents' networks, trust management becomes a pivotal issue. Defying tool for a fast and efficient partner selection, even in lack of direct information, is of paramount importance, as much as possessing mechanisms allowing a matching between a selected task and a reliable agent able to carry it out. Direct experience plays a big part, nevertheless it requires a long time to offer a stable and accurate performance. In accordance with the literature, we believe that category-based evaluations and inferential processes represent a useful resource for trust assessment. Within this work, by the means of simulations, we investigated how efficient this inferential strategy is, with respect to direct experience, focusing on when and to what extent the first prevails on the latter. Our results show that in some situations it provides even better results.