Abstract: Traditional Chinese text chunking approach is to identify phrases using only one model and same features. It has been shown that the limitations of using only one model are that: the use of the same types of features is not suitable for all phrases and data sparseness may also result. In this study, the divide-conquer approach is proposed and applied in the identification of Chinese phrases. This strategy divides the task of chunking into several sub-tasks according to sensitive features of each phrase and identifies different phrases in arallel. Then, a two-stage decreasing conflict strategy is used to synthesize each sub-task�s answer. Through esting on Chinese Penn Treebank, F score of Chinese chunking using Multi-agent strategy achieves to 95.23%, which is higher than the best result that has been reported.