The purpose of this paper is to develop and study algorithms for interaction of Software Agents in group decision making support systems, intended for logistic problems of control of transport flows in electronic business. The paper regards the problem of modeling and solution of the problem of minimization of transportation costs and idle time of vehicles for the chosen version of the route and schedule at multiple urban crossings. The authors offer a generalized algorithm for solution of the problem of drawing up an optimum schedule for traffic through multiple urban crossings with the use of Software Agents and computer models of transport flow. It is also supposed that Software Agents can change the duration of one-type operations on separate processors and can interact in search of the best solution. At the same time modeling program is a Software Agent controlling vehicles under consideration, while the program of data collecting and analysis is a Supra Software Agent, which makes the optimum processors’ operating schedule with the help of a group decision making support system. The processor is the traffic lights of the urban crossroads, and the operation is handling of a transport flow to an assigned direction and assigned time.