Aiming at the uncertainty and dynamism in agile manufacturing and the features of Hybrid Flow Shop (HFS) scheduling problem, a multi-Agent based dynamic scheduling system for hybrid flow shop was developed, which consists of management Agent, strategy Agent, job Agent and machine Agent. First, a HFS aimed Interpolation Sorting (HIS) algorithm was proposed and integrated into the strategy Agent, which is suitable for static scheduling and dynamic scheduling under a variety of dynamic events. Then the coordination mechanism between the various Agents was designed. In the process of production, all Agents worked independently and coordinate with each other according to their behavioral logic. If a dynamic event occurred, the strategy Agent called HIS algorithm to generate the sequence of jobs according to the current workshop state, and then the Agents continued to coordinate according to the generated sequence until the production was finished. Finally, simulations of dynamic scheduling such as machine failure, rush order and online scheduling were carried out. The experimental results show that compared with a variety of scheduling rules, HIS algorithm has better schedule results than those by scheduling rules in these cases; especially in machine breakdown rescheduling, the consistency of makespan before and after rescheduling was up to 97.6%, which means that the HFS dynamic scheduling system is effective and flexible.