Argue to agree: A case-based argumentation approach

The capability of reaching agreements is a necessary feature that large computer systems where agents interoperate must include. In these systems, agents represent self-motivated entities that have a social context, including dependency relations among them, and different preferences and beliefs. Without agreement there is no cooperation and thus, complex tasks which require the interaction of agents with different points of view cannot be performed. In this work, we propose a case-based argumentation approach for Multi-Agent Systems where agents reach agreements by arguing and improve their argumentation skills from experience. A set of knowledge resources and a reasoning process that agents can use to manage their positions and arguments are presented. These elements are implemented and validated in a customer support application.

► We propose a reasoning process for agents to manage positions and arguments.
► Agents engage in argumentation processes taking into account their social context.
► Agents that follow an argumentation policy provide more accurate solutions.
► If an argumentative agent has enough domain-knowledge gets better position acceptance.
► As the argumentation knowledge of one agent increases, the agreement also increases.