In recent years, friending recommendation has played a crucial role on the explosive growth of online social networks. Prior studies on this problem have the following two limitations: i) they assume that there is only one pair of source and target at one time; and ii) the intermediate user can indefinitely forward friending requests. These two assumptions are impractical for online social networks. To bridge this gap, we study how to maximize the acceptance probability for multi-pair active friending in online social networks. In this paper, we first establish a probability model for the Multi-pair Active Friending with Tolerance and then propose two efficient algorithms: Multi-pair Active Friending algorithm for Conflict Resolution (MAFCR) and Group-based Multi-pair Active Friending algorithm for Conflict Resolution (MAFCR-G). Through extensive experiments, we show that the algorithm MAFCR significantly outperforms the baseline algorithm in terms of average acceptance probability, and the algorithm MAFCR-G greatly reduces the running time while obtaining similar average acceptance probability.