The architecture we are introducing in this article is a hybrid one. It combines vertical and horizontal hybrid approachs where each layer is based on a subsumption architecture.
The aim of our approach is to study the possibility to obtain a cooperative behavior within a multi-agents system without using centralized control; and thus to observe the emergence of potential relations between an agent and the society to which it belongs.
RobocCup-99 Team Descriptions. Simulation League
 Paul Davidsson A Linearly Quasi-Anticipatory Autonomous Agent Architecture: Some preliminary experiments; in Distributed Artificial Intelligence Architecture and Modelling (Lecture Notes in Artificial Intelligence 1087); C. Zhang and D. Lukose (ed.); pages 189-203; Springer Verlag; 1996.
 Bertil Ekdahl; Eric Astor et Paul Davidsson Towards Anticipatory Agents. In M. Wooldridge and N.R. Jennings; editors; Intelligent Agents - Theories; Architectures; and languages; Lecture Notes in Artificial Intelligence 890; page 191- 202; Springer Verlag; 1995.
 Jrg P. Mller The design of intelligent Agents; volume 1177 of Lecture Notes in Artificial intelligence. Springer-Verlag; 1996.
 Christoph G. Jung Experimenting with Layered; Ressource- Adapting Agents in the RoboCup Simulation in M. Asada (ed.); RoboCup-98: Robot Soccer WorldCup II; Lecture Notes in Artificial Intelligence; Springer; 1999.
 Hayes-Roth B. An architecture for adaptative intelligent systems. Artificial Intelligence; 72(1-2):pp. 329-365; january 1995.