Abstract
Software agents representing supply chain partners make it possible to automate supply chain management and particularly can address the challenging problem of automating the process of dynamic supply chain formation. This paper puts forward an extended contract net mechanism for dynamic supply chain formation and applies it to China petroleum supply chain management, which is characterized by a semi-monopolized market, where conventional negotiation protocols are limited because they are based on the assumption of a pure market. The proposed multi-agent negotiation mechanism is algorithmized and validated in two scenarios of dynamic supply chain formation, i.e., semi-monopolized market and emergency, respectively.