This paper unifies two recent strands of research in multiagent system design. One, commitments are widely recognized as capturing important aspects of interactions among agents, but current approaches tend to emphasize individual commitments and typically restrict themselves to interactions between pairs of agents. Two, methodologies for multiagent system design tend to consider protocols and coordination requirements among agents, but do not seriously accommodate commitments. This paper proposes a methodology to infer commitments from an example conversation among various parties. Based on the conversation, we first build a commitment causality diagram indicating the causal relations among the commitments. Using this diagram, we generate behavior models for each role. We show that models produced by this approach successfully capture commitment-level protocols and allow flexible implementation of non-commitment communications as long as the commitment causal relations are followe...
Feng Wan, Munindar P. Singh