Towards a Model of Cognitive Agents: Integrating Emotion on Trust

Abstract

Open multi-agent systems are those in which the agents can enter or leave the system freely and entities with unknown intentions can occupy the environment. In these systems, trust and reputation mechanisms are used to choose partners in order to delegate tasks. Most of the trust and reputation models proposed in the literature take into account their functional aspects, but not how they affect the reasoning cycle of the agent. That is, under the agent's perspective, a trust model is usually just a "black box". In this paper we propose a model definition in which trust processes are part of the agents' reasoning cycle, influencing and being influenced by the emotions of the agent. Our model is inspired in BDI approach and is defined as a multi-context system.