An Architecture for Agents with Obligations

We explore the view that coordinated behavior is driven by the social constraints (e.g. obligations and interdictions) that agents in organizations are subject to. In this framework, agents adopt those goals that are requested by their obligations, knowing that not fulllling obligations induces a price to pay or a loss of utility. Based on this idea we build a coordination system where we represent the organization, the roles played by agents, the obligations imposed among roles, the goals and the plans that agents may adopt. To consistently update an agent's obligations and interdictions we present an incremental propagation method that also helps with detecting and deciding between connicting obligations. Once a goal adopted, a special brand of plans, called conversation plans, are available to the agents for eeectively carrying out coordinated action. Conversation plans explicitly represent interactions by message exchange and their actions are dynamically reordered using the theory of Markov Decision Processes to ensure the optimization of various criteria. The framework is applied to model supply chains of distributed enterprises.