Life-like agents have the potential to make e-shopping sites on the Web more attractive and persuasive; our interest is to determine how multiple life-like agents should behave as a team to persuade customers. To know how the social relationships among two agents and a human user impacts the e ectiveness of persuasion from the viewpoint of the balance theory, we develop a multi-agent persuasion system. In the system, the agents construct a social relationship to the user, and they then try to persuade him/her to select items that they recommend. An evaluation shows that a balanced relationship yields better performance than an imbalanced one.