In an effort to composite an optimal supply chain, this study has introduced an agent-based negotiation model as a method for assigning a lot of orders to a large number of participants. As a resources allocation mechanism to form strategic cooperation based on information sharing between supply chain members, this agent negotiation model provides such functions as bidding, scheduling, and coordination, allowing all participants to make a profit, and accomplishing a Pareto-optimum solution from the viewpoint of the whole supply chain. SET model-based scheduling takes into consideration both early (earliness) production costs and late (tardiness) production costs, along with the competitive relationship between multiple participants. This study has tried to prove that the result of an agent-based negotiation is a Pareto optimal solution under a dynamic supply chain environment, establishing the mathematical formulation for a performance test, and making a comparison with the heuristic Branch & Bound method.

A multi-agent technology has emerged as new paradigms that can flexibly and promptly cope with various environmental changes and complex problems. Accordingly, many studies have been carried out to establish multi-agent systems in an effort to solve dynamic problems in many fields. However, most previous research on the multi-agent frameworks aimed at, on the behalf of a user, exchanging and sharing information among agents, reusing agents, and suggesting job cooperation in order to integrate and assimilate heterogeneous agents. That is, their frameworks mainly focused on the basic functions of general multi-agents. Therefore, they are not suitable to the development of the proper system for a specific field such as a negotiation. The goal of this research is to design a multi-agent framework for the negotiation system that supports the evaluation of the negotiation messages, management of the negotiation messages, and message exchanges among the negotiation agents.

In this research, we have developed a Multi-Agent based Negotiation Support System to enhance the competitive power of a company in dynamic environments and correspond to various orders from customers by capitalizing on electronic commerce. The system uses the agent technology that comes to light as a new paradigm in dynamic environment and flexible system framework. The multi-agent technology is used to solve these problems through cooperation between agents. The system consists of six sub agents: mediator, manufacturability analysis agent, process planning agent, scheduling agent, selection agent and negotiation strategy building agent. In this paper, the proposed Multi-Agent based Negotiation Support System aims at the automation of transaction process from order to manufacturing plan through negotiation automation that is the most important in a series of business transactions.

Today, there are several markets in cyber space where companies trade electronically due to the development of Information Technology. On the other hand, the most important thing in trades is negotiation. So, in order to support current business practices as well as new ones on the Internet, electronic commerce systems need an ability to negotiate. In this paper, proposed is a method by which a seller can be supported by an agent which plays a role in negotiation process among small and medium companies, especially injection mold manufacturer. If the manufacturing capacity cannot afford to produce all orders, the manufacturer may want to extend due dates and the buyers may want to discount prices. The negotiation agent discussed in this paper cooperates with the schedule agent to get due-date information, and performs a role in one (seller)-to-many (buyer) negotiation processes.