Abstract. Most existing work on knowledge representation and reasoning assumes that the updating of beliefs is performed off-line, and that reasoning from the beliefs is performed either before or after the beliefs are changed. This imposes that, if an update occurs while reasoning is performed, reasoning has to be stopped and re-started anew so that the update is taken into account, with an obvious wastage of reasoning effort. In this paper, we tackle the problem of performing belief updating on-line, while reasoning is taking place by means of an abductive proof procedure.