Hilton José Silva de Azevedo

Agent and multi-agent applications to support distributed communities of practice: a short review

This paper concerns the relationship between agents or multi-agent systems and distributed communities of practice. It presents a review of a number of agent and multi-agent applications with features that could contribute to supporting distributed communities of practice. The association is promising because of features like autonomy, pro-activity, flexibility or ability to integrate systems that characterize agents and multi-agent systems. Furthermore, such an association is a step towards building mixed communities of humans and artificial agents. To understand how agents and multi-agent systems could answer some of the needs of distributed communities of practice, we organize the analyzed applications into five different categories defined by considering the main activities of a community, namely: Individual Participation, Synchronous Interactions, Asynchronous Interactions, Publishing and Community Cultivation. Such a classification helps us identify the relevant features of the current technology and determine some that should be further developed, e.g. to support community coordination or gather information related to virtual communities. For each application we selected, we present its main approach and point out its potential interest.

Using asymmetric keys in a certified trust model for multiagent systems

We present a contribution based on encryption to the model for the certification of trust in multiagent systems. The originality of the proposal remains in the use of asymmetric keys that allow the local storage of testimonies with the service agents that were assessed. The aim is to raise the level of efficiency that client agents have when contracting specialized service agents. To reach this objective we make three hypotheses: (i) client agents are able to measure and inform the quality of a service they receive from a service agent; (ii) distributed certificate control is possible if every service agent stores the certificates it receives from its client agents and, (iii) the content of a certificate can be considered safe as long as the public and private keys used to encrypt the certificate remain safe. This approach reduces some weak points of trust models that rely on the direct interaction between service and client agents (direct trust) or those that rely on testimony obtained from client agents (propagated trust). Simulation showed that encrypted certificates of trust improved the efficiency of client agents when choosing their service provider agents. The reason seems to be that the reputation of a given service provider agent is based on the reputation it has among the totality of client agents that used its services.

Encrypted certified trust in multi-agent system

We present a model for the certification of trust in multi-agent systems based on encryption. The objective is to raise the level of efficiency that client agents have when contracting specialized service agents. We make three hypotheses: (i) client agents are able to measure and inform the quality of a service they receive from a service agent; (ii) distributed certificate control is possible because every service agent stores the certificates it receives from its client agents and, (iii) the content of a certificate can be considered safe as long as the public and private keys used to encrypt the certificate remain safe. This approach reduces some weak points of trust models that rely on the direct interaction between service and client agents (direct trust) or those that rely on testimony obtained from client agents (propagated trust). Simulation showed that encrypted certificates of trust improved the efficiency of client agents when choosing their service provider agents. The reason seems to be that the reputation of a given service provider agent is based on the reputation it has among the totality of client agents that used its services.

Pedagogic coherence in virtual didactic authoring communities

Although good content correctness can be observed on the web, one may have difficulty finding a set of entries covering a complete syllabus of a course with a coherent pedagogic approach. We conducted an experiment to test the hypothesis if a collection of didactic contents can be discussed, distributed and produced by an online community of teachers sharing the same subject of interest. The ¿negotiation of meaning¿, a concept present in the Communities of Practice Model, inspired the design of this experiment, which evolves in a virtual environment, rendering possible the exchange of ideas on didactic material judged necessary for class use. We present the main lines of the method as well as the results obtained from 39 grade school teachers divided in seven groups. The results showed that the adoption of activities in the method aroused in the participants a high level of satisfaction in relation to the didactic content they had produced; despite their lack of experience dealing with virtual environments.

Work in progress - towards a tool to analyze qualitative aspects of the relations among members of social networks

This paper discusses a tool to study the relations among group members of a social network that evolve using a virtual environment. Understanding how these relations are built and maintained is essential to foster favorable conditions that can facilitate collective and individual learning. The focus of interest is how inner relations affect both the collective and individual learning of its members. We consider a group as being a set of relations among people and artifacts. As an example, we might determine which relations among members of a Project Team (predominantly goal-oriented) are different from the ones found in Communities of Practice (predominantly learning-oriented), and how they affect the learning of their members. We propose to characterize the relations among members by analyzing text content of social exchanges (e.g. email messages, blog posts, chat sessions, etc). The approach originality relies on taking into account the distinct points of view of its actors. Due to the distributed character of the problem (a virtual group), we intend to develop this tool by using a Multi- Agent System, whose architecture we present in this paper.

Certified Trust Model

This paper presents a certified confidence model which aims to ensure credibility for information exchanged among agents which inhabit an open environment. Generally speaking, the proposed environment shows a supplier agent b which delivers service for a customer agent a. The agent a returns to b a crypto-graphed evaluation r on the service delivered. The agent b will employ R as testimonial when requested to perform the same task for a distinct customer agent. Our hypotheses are: (i) control over testimonials can be distributed as they are locally stored by the assessed agents, i.e., each assessed agent is the owner of its testimonials; and (ii) testimonials, provided by supplier agents on their services, can be considered reliable since they are encapsulated with public key cryptography. This approach reduces the limitations of confidence models based, respectively, on the experience resulted from direct interaction between agents (direct confidence) and on the indirect experience obtained from reports of witnesses (propagated confidence). Direct confidence is a poor-quality measure for a customer agent a hardly has enough opportunities to interact with a supplier agent b so as to grow a useful knowledge base. Propagated confidence depends on the willingness of witnesses to share their experiences. The empiric model was tested in a multiagent system applied to the stock market, where supplier agents provide recommendations for buying or selling assets and customer agents then choose suppliers based on their reputations. Results demonstrate that the confidence model proposed enables the agents to more efficiently choose partners.

An Open Multiagent Architecture to Improve Reliability and Adaptability of Systems

We present an open multiagent architecture for intelligent collaborative information systems based on the concepts of cognitive agents and machine learning. We assume a double hypothesis: (i) agents collaborate to reach their goals; (ii) agents can find and interact with other agents in a network. This assumption implies specialized services that have as functions: (a) relate the needs of user agents with the services of supplier agents; (b) integrate several answers in order to produce better results; (c) send regular notification to user agents about changes in the world. The location of such services depends on the architecture one adopts. We focus on the definition of architecture able to dynamically integrate new agents into the system. Thus, agents shall have machine learning capabilities inherited from a generic agent. An open architecture brings some benefits to the system performance such as adaptability, availability of services, incremental development and improvement of lifetime. System proactive capabilities may extend the knowledge human users have about the process.