This paper describes a new model for robust predictive/reactive scheduling of steel continuous casting based on the use of multi-agents, tabu search and heuristic approaches. A continuous caster agent generates a predictive production schedule taking into account manufacturing requirements and local constraints using tabu search. The predictive schedule is modifies so as to minimize deviation between the performance measure values of the realized and predictive schedules in order to react to real-time events. We propose several schedule-repair and complete reschedule strategies to handle the real-time events, evaluate and compare their performance. The decision as to whether to locally repair the schedule or reschedule from scratch (complete reschedule) is based on three measures: robustness, utility and stability. Utility measures the change in schedule objective following schedule revision. Stability measures the deviation from the original schedule caused by schedule revision to quantify the undesirability of making large changes to the initial predictive schedule unless absolutely necessary. Robustness combines the utility and stability measures. In order to investigate the performance of these measures and strategies, simulation experiments were carried out and results are reported.