To enhance the evacuation efficiency in partially observable asymmetric-exit evacuation, a general framework of dynamic guiding assistant system with density control algorithm is investigated. In this framework, several evacuation assistants are established to observe the partial information of pedestrians' location and adjust the guiding signals of the dynamic guiding assistant systems. A simple on-off-based density control algorithm is proposed for the evacuation assistants according to the delayed data of the observed information (i.e., pedestrian densities in the observed regions near the corresponding exits). By involving a force-driven cellular automaton model, the strategic suggestions on how to set the observed region and the target density are given in this paper. It is observed that the proposed density control algorithm can control (positively affect) the global distribution of the pedestrians' locations and suppress arching phenomena in the evacuation process even using the observed partial information under time delays. By imposing a moderate target density, the dynamic guiding assistant system also suppresses the triggers of collisions around the exits and avoids separating the pedestrians to an inefficient way. We reveal an interesting fact without loss of generality that to enhance the evacuation efficiency, we only need to observe the pedestrians' location from a small region near the exit instead of a large region when the time delay of the observed information is small enough. Our numerical findings are expected to provide some new insights on designing the computer-aided guiding strategies in the real evacuations.