Behaviour Flexibility in Dynamic and Unpredictable Environments: The ICAGENT Approach. Vangelis Kourakos-Mavromichalis and George Vouros Dept. Of Information and Communication Systems Engineering University of the Aegean Karlovassi, Samos – Greece {emav, georgev}@aegean.gr Abstract. Several agent frameworks have been proposed for developing intelligent software agents and multi-agent systems that are able to perform in dynamic environments. These frameworks and architectures exploit specific reasoning tasks (such as option selection, desire filtering, plan elaboration and means-end reasoning) that support agents to react, deliberate and/or interact/cooperate with other agents. Such reasoning tasks are realized by means of specific modules that agents may trigger according to circumstances, switching their behaviour between predefined discrete behavioural modes. This paper presents the facilities provided by the non-layered BDI-architecture of ICAGENT for supporting performance in dynamic and unpredictable multi-agent environments through efficient balancing between behavioural modes in a continuous space. This space is circumscribed by the purely (individual) reactive, the purely (individual) deliberative and the social deliberative behavioural modes. In a greater extend than existing frameworks; ICAGENT relates agent’s flexible behaviour to cognition and sociability, supporting the management of plans constructed by the agent’s mental and domain actions in a coordinated manner. 1 Introduction This paper focuses on agents’ autonomous behaviour in dynamic and non-deterministic environments that are populated by multiple agents. Being resource-bounded, an agent that performs in such environments faces inherent limitations with respect to the perception, practical reasoning, performance and cooperation abilities: It cannot be fully aware of the changes that occur in their physical environment, the available time to compute responses is always limited and bounded to the time that it has until its resources exceed, it has to plan and to achieve its goals without exceeding environmental and own resources, and finally, it often needs to collaborate with others to achieve better results (e.g. it can save resources, or increase its expected utility or its fitting advantage). To overcome the above limitations, a resource bounded agent must be able to deliberate, to plan and act with respect to its own, others’, and environment resources, adapting to unforeseen events and to newly detected facts, either individually or in collaboration with others. On the other hand, an agent needs to react to events/facts that provide opportunities for achieving its goals or to events/facts that may seriously affect its