Crisis management challenges decision support systems designers. One problem in the decision marking is to develop systems able to help the coordination of the different involved teams. Another challenge is to make the system work with a degraded communication infrastructure. Each workstation or embedded application must be able to help to make a decision with a degraded network by taking into account the potential decisions made by other agents. We propose in this article a multi-agent model, based on an ant colony optimization, and designed to manage the complexity in the deployment of resources to solve a crisis. This model is able to manage data uncertainty, and its global goal is to optimize, in a stable way, fitness functions, like saving lives, defined by multiple users. Moreover, thanks to a reflexive process, the model is able to manage the effects into the environment of its decisions, in order to take more appropriate decisions. Thanks to our transactional model, the system is also able to take into account a large data amount without exploring all potential solutions. The graphical interface should be able to make the user defining rules database. %Each rule associates, for each potential event, a goal with its fitness functions, and a list of possible tasks to do. Then, if the nature of the crisis is deeply unchanged, users should be able to change rules' databases.