Abstract: To solve the disadvantages of the basic ant colony algorithm including slow convergent speed and incidental stagnation behavior, a new ant colony optimization algorithm, named the ant system with scouting subgroup (ASSS), was proposed. In the algorithm a small part of ants were separated and formed a scouting subgroup that random moved at a certain probability to increase results diversity. The pheromone update strategy used the iteration-best-ant and global-best-ant at the same time to make use of both iteration-fruit and history-fruit. LK mutation factor was employed to locally optimize the search results of each step. Three typical traveling salesman problems (TSP) were tested, and the results show that this proposed algorithm can avoid prematurity and speed up convergence.