. We describe the user modeling and personalization techniques adopted in SETA, a prototype toolkit for the construction of adaptive Web stores which customize the interaction with users. The Web stores created using SETA suggest the items best fitting the customers' needs and adapt the layout and the description of the store catalog to their preferences and expertise. SETA uses stereotypical information to handle the user models and applies personalization rules to dynamically generate the hypertextual pages presenting products. The system adapts the graphical aspect, length and terminology used in the descriptions to parameters like the user's receptivity, expertise and interests. Moreover, it maintains a model associated with each person the goods are selected for; in this way, multiple criteria can be applied for tailoring the selection of items to the preferences of their beneficiaries. Keywords: user modeling, personalized information presentation, customization of Web stores, ...

RETSINA is an implemented Multi-Agent System infrastructure that has been developed for several years and applied in many domains ranging from financial portfolio management to logistic planning. In this paper, we distill from our experience in developing MASs to clearly define a generic MAS infrastructure as the domain independent and reusable substratum that supports the agents' social interactions. In addition, we show that the MAS infrastructure imposes requirements on an individual agent if the agent is to be a member of a MAS and take advantage of various components of the MAS infrastructure. Although agents are expected to enter a MAS and seamlessly and e ortlessly interact with the agents in the MAS infrastructure, the current state of the art demands agents to be programmed with the knowledge of what infrastructure they will utilize, and what are various fallback and recovery mechanisms that the infrastructure provides. By providing an abstract MAS infrastructure model and a concrete implemented instance of the model, RETSINA, we contribute towards the development of principles and practice to make the MAS infrastructure "invisible" and ubiquitous to the interacting agents.

. A critical challenge to creating effective multi-agent systems is allowing them to operate effectively in environments where failures (`exceptions') can occur. This paper describes the motivation, progress and plans for work being pursued in this area by the MIT Adaptive Systems and Evolutionary Software research group (http://ccs.mit.edu/ases/). 1. The Challenge: Enabling Robust Open Multi-Agent Systems "open systems ... represent arguably the most important application for multiagent systems" (Wooldridge, Jennings et al. 1999) This paper addresses one simple question: how can we develop effective multi-agent systems out of the diverse and unreliable (buggy, malicious, or simply "dumb") agents and infrastructures we can expect to encounter in open system contexts? This is becoming an increasingly critical question because of emerging changes in the way human organizations work. Globalization, enabled by ubiquitous telecommunications, has increasingly required that organizations ...

With the recent expansion of the Internet, the interest towards electronic sales has quickly grown and many tools have been built to help vendors to set up their Web stores. These tools offer all the facilities for building the store databases and managing the order processing and secure payment transactions, but they typically do not focus on issues like the personalization of the interaction with the customers. However, Web surfers are generally heterogeneous and have different needs and preferences; moreover, the trend of marketing strategies is to pay more and more attention to the specific buyers. So, the importance of personalizing the interaction with the user and the product presentation is increasing. In this paper, we describe the architecture of a configurable virtual Web store supporting personalized hypertextual interactions with users. Our system builds a user profile by applying user modeling techniques and stereotypical information about the characteristics of customer groups; this profile is used during the interaction in order to tailor the product descriptions and the selection of items to recommend to the user's needs, varying the layout of the hypertextual pages and the detail of the descriptions accordingly. Tailoring the system's behavior requires the parallel execution of several complex tasks during the interaction (e.g. identifying the user's preferences, selecting the products most suited to her, dynamically generating the hypertextual pages). Therefore, we have defined a multiagent architecture where these tasks

In this paper we present sofar, a versatile multi-agent framework designed for Distributed Information Management tasks. sofar embraces the notion of proactivity as the opportunistic reuse of the services provided by other agents, and provides the means to enable agents to locate suitable service providers. The contribution of sofar is to combine some ideas from the distributed computing community with the performative-based communications used in other agent systems: communications in sofar are based on the startpoint/endpoint paradigm, which is the foundation of Nexus, the communication layer at the heart of the Computational Grid. We explain the rationale behind our design decisions, and describe the predefined set of agents which make up the core of the system. Two distributed information management applications have been written, a general query architecture and an open hypermedia application, and we recount their design and operations.

contracts consisting of one or a few independent issues and tractable contract spaces. Many real-world contracts, by contrast, are much more complex, consisting of multiple inter-dependent issues and intractably large contract spaces. This paper describes a simulated annealing based approach appropriate for negotiating such complex contracts that achieves near-optimal social welfares for negotiations with binary issue dependencies.

This article puts research on socially intelligent agents (SIA) in the broader context of how humans (and other primates) perceive and interact with the social world. Phylogenetic (evolutionary) and ontogenetic (developmental) issues are discussed with respect to the social origin of primate and human intelligence and human culture. Implications for designing artifacts and for the evolvability of human societies are outlined. A theory of empathy is presented that is based on current research on the primate social brain. Research projects that investigate some of these issues are reviewed. I argue that Socially Intelligent Agents (SIA) research, although strongly linked to software and robotic engineering, goes beyond a software engineering paradigm: it can potentially serve as a paradigm for a science of social minds. A systematic and experimental investigation of human social minds and the way humans perceive the social world can result in truly social artifacts,...

Multiagent systems are a promising new paradigm in computing, which are contributing to various fields. Many theories and technologies have been developed in order to design and specify multiagent systems, however, no standard procedure is used at present. Industrial applications often have a complex structure and need plenty of working resources. They require a standard specification method as well. As the standard method to design and specify software systems, we believe that one of the key words is simplicity for their wide acceptance. In this paper, we propose a method to specify multiagent systems, namely with UML statecharts. We use them for specifying almost all aspects of multiagent systems, because we think that it is an advantage to keep everything in one type of diagram. We apply

this paper, is that agents are native components of the system. This guarantees that agents and objects can communicate with one another and the same communication fabric is used by the entire population of objects. Another distinctive trait of our approach is that we provide middleware, a software layer to facilitate the development of a hopefully wide range of applications of network computing. We are thus forced to pay close attentions to the software engineering aspects of agent development, in particular to software reuse. We decided to provide a framework for assembly of agents out of components, some of them reusable. This is possible due to the agent model we overview now and discuss in depth in Section 4.

In this paper we show how planning can be achieved by means of abduction, a form of non-monotonic reasoning, in the LUPS language. LUPS employs the recently introduced notion of Dynamic Logic Programming, whereby the knowledge representation rules, namely those representing actions, can dynamically change, crucial when agents are to be situated in evolving environments. By integrating into a single framework several recent developments in the logic programming and non-monotonic reasoning eld of research, this work contributes to a better modeling and understanding of rational agents. At the same time, it enjoys the advantages of a declarative and implementable speci cation, shortening the usual gap between theory and practice often found in logical based approaches to agents. The system integrating Dynamic Logic Programming, LUPS and Abduction, in order to achieve this form of planning, has been implemented.