Abstract—This paper surveys and analyzes the state of the art of agent-mediated electronic commerce (e-commerce), concentrating particularly on the business-to-consumer (B2C) and business-to-business (B2B) aspects. From the consumer buying behavior perspective, agents are being used in the following activities: need identification, product brokering, buyer coalition formation, merchant brokering, and negotiation. The roles of agents in B2B e-commerce are discussed through the business-to-business transaction model that identifies agents as being employed in partnership formation, brokering, and negotiation. Having identified the roles for agents in B2C and B2B e-commerce, some of the key underpinning technologies of this vision are highlighted. Finally, we conclude by discussing the future directions and potential impediments to the wide-scale adoption of agent-mediated e-commerce. Index Terms—Agent-mediated electronic commerce, intelligent agents. 1

A component-based generic agent architecture for multi-attribute (integrative) negotiation is introduced and its application is described in a prototype system for negotiation about cars, developed in co-operation with, among others, Dutch Telecom KPN. The approach can be characterised as co-operative one-toone multi-criteria negotiation in which the privacy of both parties is protected as much as possible. 1

This paper presents a new model for multi-issue negotiation under time constraints in an incomplete information setting. The issues to be bargained over can be associated with a single good/service or multiple goods/services. In our agenda-based model, the order in which issues are bargained over and agreements are reached is determined endogenously, as part of the bargaining equilibrium. In this context we determine the conditions under which agents have similar preferences over the implementation scheme and the conditions under which they have conflicting preferences. Our analysis shows the existence of equilibrium even when both players have uncertain information about each other, and each agent's information is its private knowledge. We also study the properties of the equilibrium solution and determine conditions under which it is unique, symmetric, and Pareto-optimal.

This paper presents a new model for multi-issue negotiation under time constraints in an incomplete information setting. The issues to be bargained over can be associated with a single good/service or multiple goods/services. In our agenda based model, the order in which issues are bargained over and agreements are reached is determined endogenously, as part of the bargaining equilibrium. In this context we determine the conditions under which agents have similar preferences over the implementation scheme and the conditions under which they have conflicting preferences. Our analysis shows the existence of equilibrium even when both players have uncertain information about each other, and each agent's information is its private knowledge. We also study the properties of the equilibrium solution and determine conditions under which it is unique, symmetric, and Pareto-optimal.

Abstract. This paper describes the design and evaluation of SouthamptonSCM,

The notion of agent's goals is crucial in negotiation dialogues. In fact, during a negotiation, each agent tries to make and to accept the offers which satisfy its own goals. Works on negotiation suppose that an agent has a set of fixed goals to pursue. However, it is not shown how the goals are computed and chosen by the agent. Moreover, these works handle one kind of goals: the ones that an agent wants to achieve. Recent studies on psychology claim that goals are bipolar and there are at least two kinds of goals: the positive goals representing what the agent wants to achieve and the negative goals representing what the agent rejects. In this paper, we present an argumentation-based framework which generates the goals of an agent. The framework returns three categories of goals: the positive goals, the negative ones and finally the goals in abeyance.

Automated Multi-attribute Negotiation is an important and valuable mechanism in the Navy detailing system, in order to realize efficient, distributed and “Win-Win ” matching. This report provides an extensive literature review of the existing research in Multiattribute Negotiations in the fields of Economics and Artificial Intelligence, discussing the motivation for multi-attribute negotiations, as well as some difficulties in implementation. Related to Multi-attribute Negotiations, approaches to preference elicitation and multi-criteria-decision-making are also reviewed. Based on the existing literature, we conclude that multi-attribute negotiation is an important as well as Multi-attribute negotiation is a negotiation that involves multiple issues and they need to be negotiated simultaneously. Usually it is characterized by the situations in which two or even more parties 1 recognize that the differences of interest over multiple issues but also the value of cooperation exists between them and in which they want to seek a

Software agents are increasingly being used to represent humans in online auctions. Such agents have the advantages of being able to systematically monitor a wide variety of auctions and then make rapid decisions about what bids to place in what auctions. They can do this continuously and repetitively without losing concentration. To provide a means of evaluating and comparing (benchmarking) research methods in this area the trading agent competition (TAC) was established. This competition involves a number of agents bidding against one another in a number of related auctions (operating different protocols) to purchase travel packages for customers. Against this background, this paper describes the design, implementation and evaluation of SouthamptonTAC, one of the most successful participants in both the Second and the Third International Competitions. Our agent uses fuzzy techniques at the heart of its decision making: to make bidding decisions in the face of uncertainty, to make predictions about the likely outcomes of auctions, and to alter the agent's bidding strategy in response to the prevailing market conditions.

In this paper, we employ the fuzzy repertory table technique to acquire the necessary domain knowledge for software a ents to act as sellers and buyers usin a bilateral, multi-al,g ne otiation model that can achieve optimal results in semi-competitive environments.

Abstract not found