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

Abstract. The scientific research in the area of computational mechanisms for trust and reputation in virtual societies is a recent discipline oriented to increase the reliability and performance of electronic communities. Computer science has moved from the paradigm of isolated machines to the paradigm of networks and distributed computing. Likewise, artificial intelligence is quickly moving from the paradigm of isolated and non-situated intelligence to the paradigm of situated, social and collective intelligence. The new paradigm of the so called intelligent or autonomous agents and Multi-Agent Systems (MAS) together with the spectacular emergence of the information society technologies (specially reflected by the popularization of electronic commerce) are responsible for the increasing interest on trust and reputation mechanisms applied to electronic societies. This review wants to offer a panoramic view on current computational trust and reputation models.

A diverse collection of trust-modeling algorithms for multi-agent systems has been developed in recent years, resulting in significant breadth-wise growth without unified direction or benchmarks. Based on enthusiastic response from the agent trust community, the Agent Reputation and Trust (ART) Testbed initiative has been launched, charged with the task of establishing a testbed for agent trust- and reputation-related technologies. This testbed serves in two roles: (1) as a competition forum in which researchers can compare their technologies against objective metrics, and (2) as a suite of tools with flexible parameters, allowing researchers to perform customizable, easily-repeatable experiments. This paper first enumerates trust research objectives to be addressed in the testbed and desirable testbed characteristics, then presents a competition testbed specification that is justified according to these requirements. In the testbed’s artwork appraisal domain, agents, who valuate paintings for clients, may gather opinions from other agents to produce accurate appraisals. The testbed’s implementation architecture is discussed briefly, as well.

Traditional centralized approaches to security are difficult to apply to large, distributed, multi-agent systems. Developing a notion of trust that is based on the reputation of agents can provide a softer notion of security that is sufficient for many MAS applications. However, designing a reliable and "trustworthy" reputation mechanism is not a trivial problem. In this paper, we address the issue of incentive-compatibility, i.e. why should agents report reputation information and why should they report it truthfully. By introducing a side-payment scheme organized through a set of broker agents we make it rational for software agents to truthfully share the reputation information they have acquired in their past experience. The theoretical results obtained were verified by a simple simulation.

Existing e-markets presumes no deception at agents or employed simple mechanisms to counter-act deception. However, the reality shows agents in e-markets can either cheat or break contacts due to higher benefits elsewhere and is similar to what a human society is. Accordingly, the notion of trust in a human society should be implemented in e-markets. Most of existing researches on trust molded trust theoretically from different views, and hence is not easy to get them deployed in e-markets due to the essence of non-computability. However, current computable trust mechanisms, such as those in eBay and Nextag, uniformly manipulate trust involved in all trading, resulting in complaints about none-differentiable experience. On the other hand, a computable trust model can help the formation of coalitions in e-markets and gain market warfare. In this paper, we present a new computable trust model absorbing major views of trust with which agents in e-markets can better evaluate ones to be possibly traded with before trading processes take place. In this model, trust is characterized with the properties of being computable, individualized, evolutional, represented by scores, and extendable to the computation of coalition trust. 1.

Abstract. A mobile agent is an autonomous agent that is not bound to the system on which it begins execution. Unfortunately, the mobility and interaction inherent in mobile agent technology introduces significant security problems, such as malicious host attacks, which can disable the agent, alter its code, or disrupt its communication. This research explores distributed security solutions based on cooperating agents that communicate host trustworthiness assessments to protect each other from malicious hosts. In addition, trust-based strategies are examined by which mobile agents assist each other in avoiding malicious hosts and recovering from host attacks. Communication among agents is vital to robust soft security to ensure that agents can cooperate by sharing their host trustworthiness assessments. Since agent mobility inherently makes communication difficult, unreliable, or sometimes impossible, this research conducts experiments to examine the affect of communication link disruption on distributed trust assessment techniques to pave the way for future security solutions that accommodate inter-agent communication problems. The experiments demonstrate that agent communication can be used to ensure accurate trust assessments; only a small fraction of possible communication links is required for accurately identifying and avoiding malicious hosts. 1

Abstract. We analyze a mechanism that provides strong incentives for the submission of truthful feedback in virtual communities where services are exchanged on a peer-to-peer basis. Lying peers are punished with a severity that is exponential to their frequency of lying. We had first introduced and evaluated experimentally the mechanism in [1]. In this paper, we develop a Markov-chain model of the mechanism. Based on this, we prove that, when the mechanism is employed, the system evolves to a beneficial steady-state operation even in the case of a dynamically renewed population. Furthermore, we develop a procedure for the efficient selection of the parameters of the mechanism for any peer-to-peer system; this procedure is based on ergodic arguments. Simulation experiments reveal that the procedure is indeed accurate, as well as effective regarding the incentives provided to participants for submitting truthful feedback. 1

Abstract not found