Open Multi-agent Systems Research Articles

An abstract architecture for virtual organizations: The THOMAS approach

Today, the need for architectures and computational models for large-scale open multi-agent systems is considered to be a key issue for the success of agent technology in real-world scenarios. This paper analyzes the significant unsolved problems that must be taken into account in order to develop real, open multi-agent systems. It identifies requirements and related open issues, discusses how some of these requirements have been tackled by current technologies, and explains how the THOMAS architecture is able to give support to these open issues. This paper also describes the THOMAS abstract architecture and computational model for large-scale open multi-agent systems based on a service-oriented approach that specifically addresses the design of virtual organizations. An application example for the management of a travel agency system, which demonstrates the new features of the proposal, is also presented.

Statistical relational learning of trust

The learning of trust and distrust is a crucial aspect of social interaction among autonomous, mentally-opaque agents. In this work, we address the learning of trust based on past observations and context information. We argue that from the truster’s point of view trust is best expressed as one of several relations that exist between the agent to be trusted (trustee) and the state of the environment. Besides attributes expressing trustworthiness, additional relations might describe commitments made by the trustee with regard to the current situation, like: a seller offers a certain price for a specific product. We show how to implement and learn context-sensitive trust using statistical relational learning in form of a Dirichlet process mixture model called Infinite Hidden Relational Trust Model (IHRTM). The practicability and effectiveness of our approach is evaluated empirically on user-ratings gathered from eBay. Our results suggest that (i) the inherent clustering achieved in the algorithm allows the truster to characterize the structure of a trust-situation and provides meaningful trust assessments; (ii) utilizing the collaborative filtering effect associated with relational data does improve trust assessment performance; (iii) by learning faster and transferring knowledge more effectively we improve cold start performance and can cope better with dynamic behavior in open multiagent systems. The later is demonstrated with interactions recorded from a strategic two-player negotiation scenario.

OMAS—a flexible multi-agent environment for CSCWD

CSCW requires efficient support to distributed teams. Several technologies seem to be good candidates for supporting CSCW among which groupware or agents. Groupware is efficient but rather inflexible, multi-agent systems are more flexible but difficult to implement. OMAS (Open Multi-Agent System) is a multi-agent platform derived from a number of previous research projects and teaching courses. With OMAS we tried to answer the problems of architecture, skill definition, protocol implementation, ontologies, dialog using natural language, and debugging, so as to simplify the work of an application designer. OMAS uses a “plug in” type approach offering a model of generic cognitive agent. Agents are of three types: service, personal assistants and transfer. They are organized as coteries, meaning that each agent sees all messages. Agents have separate ontologies and tasks models. Agents are multi-threaded and can execute several tasks concurrently. Personal assistants have prototype dialogs and vocal interface. OMAS has been designed for supporting CSCWD projects or applications. It can be downloaded from the Internet.

Executable specification of open multi-agent systems

Multi-agent systems where the agents are developed by parties with competing interests, and where there is no access to an agent’s internal state, are often classified as ‘open’. The members of such systems may inadvertently fail to, or even deliberately choose not to, conform to the system specification. Consequently, it is necessary to specify the normative relations that may exist between the members, such as permission, obligation, and institutional power. We present a framework being developed for executable specification of open multi-agent systems. We adopt a bird’s eye view of these systems, as opposed to an agent’s perspective whereby it reasons about how it should act. This paper is devoted to the presentation of various examples from the NetBill protocol formalised in terms of institutional power, permission and obligation. We express the system specification in the Event Calculus and execute the specification by means of a logic programming implementation. We also give several example formalisations of sanctions for dealing with violations of permissions and obligations. We distinguish between an open multi-agent system and the procedure by which an agent enters and leaves the system. We present examples from the specification of a role-management protocol for NetBill, and demonstrate the interplay between such a protocol and the corresponding multi-agent system.

The THOMAS architecture in Home Care scenarios: A case study

Today, the need for architectures and computational models for large scale open multi-agent systems is considered a key issue for the success of agent technology in real world scenarios. The main goal of this paper is to describe a case study in Home Care scenarios applying an abstract architecture and a computational model for large scale open multi-agent systems based on a service-oriented approach. The architecture used is THOMAS, which specifically addresses the design of Home Care systems. This paper presents services examples for the management of a dependent home environment, and demonstrates the new features of the proposal.

COMMUNICATION LANGUAGES FOR MULTIAGENT SYSTEMS

Agent Communication Languages (ACLs) have recently acquired a primary role in open multiagent systems, which need a standard communication framework shared by all interacting heterogeneous agents. According to the most important ACL standard proposals so far, agents are supposed to carry out the communication process by performing actions of a specific type, namely, communicative acts, whose semantics is defined in terms of the agents' mental states. Although following the mainstream guidelines inspired by the Speech Act Theory, our work illustrates an alternative model of agent communication, by shifting the focus from agents' mental states to their social state. Taking an existing communicative act library, we provide a semantics for a significant set of acts based on the concept of commitment, and prove that our approach tackles some issues that have not been dealt with in an effective way yet and that may have hindered the rise of an universally accepted ACL standard.

Exception representation and management in open multi-agent systems

One of the major issues in dealing with exceptions in open multi-agent systems (MAS) is lack of uniform representation of exceptions and their shared semantics. In the absence of a uniform framework different business organizations may use different representations for the same exception or may interpret the same exception in different ways. In order to address this issue we apply an ontological approach as a uniform way of representing and interpreting exceptions in cross-organizational settings. This helps agents from different organizations interpret exceptional situations in an unambiguous way and exchange exception related information using standard structures. We believe that an exception ontology along with a domain ontology increases the open MAS reliability and also enhances its fault tolerance capability. The proposed ontology is built using the ontological support provided by the JADE agent framework and exception diagnoses agents are implemented using the JACK™ agent framework.

Interaction laws for dependability explicit computing in open multi-agent systems

In an open multi-agent system (MAS), agent autonomy and heterogeneity may possibly exploit cooperation, leading the system to an undesirable state. Since an MAS has no central control, a coordination mechanism must be developed to allow agents to fulfill their design goals. It is proposed to incorporate the dependability explicit computing (DepEx) ideas into a law-governed approach in order to build a dependable open MAS. The authors show that the law specification can explicitly incorporate dependability concerns, collect data and publish them in a metadata registry. This data can be used to realise DepEx and, for example, it can help to guide design and runtime decisions. The advantages of using a law-governed approach are (i) the explicit specification of the dependability concerns; (ii) the automatic collection of the dependability metadata reusing the infrastructure of the mediators presenting in law-governed approaches; and (iii) the ability to specify reactions to undesirable situations, thus preventing service failures.

The Ingenias Project: Methods And Tool For Developing Multiagent Systems

Agent-oriented methodologies are paving the way towards the adoption of agent technology in software industry. However, there are still several issues to address: testing mechanisms, specialized verification methods, a formally defined agent oriented development process, illustrative case studies, or better development tools. This should be considered in a changing context because of innovations in related areas, which are integrated in the agent paradigm. In this paper, we show a coordinated approach to address these needs in the context of a research project, INGENIAS. The purpose of this project is to contribute to the agent-oriented software engineering field by providing, on the basis of a wellspecified software development process, an open multi-agent systems (MAS) development framework that integrates methods, techniques and tools. The paper will show problems we face in the projects and the solutions we adopt for them.

An event-driven high level model for the specification of laws in open multi-agent systems

The agent development paradigm poses many challenges to software engineering researchers, particularly when the systems are distributed and open. They have little or no control over the actions that agents can perform. Laws are restrictions imposed by a control mechanism to deal with uncertainty and to promote open system dependability. In this paper, we present a high level event-driven conceptual model of laws. XMLaw is an alternative approach to specifying laws in open multi-agent systems that presents high level abstractions and a flexible underlying event-based model. Thus XMLaw allows for flexible composition of the elements from its conceptual model and is flexible enough to accept new elements.

Learning to trust in the competence and commitment of agents

For agents to collaborate in open multi-agent systems, each agent must trust in the other agents' ability to complete tasks and willingness to cooperate. Agents need to decide between cooperative a...

From the specification to the implementation of norms: an automatic approach to generate rules from norms to govern the behavior of agents

Open multi-agent systems composed of heterogeneous, autonomous and independently designed agents are usually governed by a set of norms. The established norms regulate the behavior of the agents by pointing out their permissions, prohibitions and obligations. This paper presents a normative language to specify norms and proposes the implementation of such norms by using a rule-based system. The implementation is achieved by automatically transforming the specification of each norm of the system into a set of rules used to govern the behavior of the agents according to the norm. The governance system is able to activate and deactivate norms, to point out the norms violations and fulfillments and to inform about punishments and rewards.

Interval-Valued Hidden Markov Models for Recognizing Personality Traits in Social Exchanges in Open Multiagent Systems

This paper presents an application of Interval-valued Hidden Markov Models to the modelling of agent personality traits in multiagent systems. The agents’ behaviors are modeled as probabilistic transitions functions, where interval-valued probabilities are used to express the uncertainty in determining those probabilities. The model of regulation of social exchanges is based on the concept of equilibrium supervisor, which is able to recommend the best exchanges for the agents to perform in order to achieve the equilibrium of the system.

Conceptual modeling and development of an intelligent agent-assisted decision support system for anti-money laundering

Criminal elements in today’s technology-driven society are using every means available at their disposal to launder the proceeds from their illegal activities. In response, international anti-money laundering (AML) efforts are being made. The events of September 11, 2001, highlighted the need for more sophisticated AML and anti-terrorist financing programs across the industry and nation. In the wake of this, regulators are focusing on the role that technology can play in compliance with laws and ultimately in law enforcement. Banks will have to employ or enhance AML tools and technology to satisfy rising regulatory expectations. While many AML solutions have been in place for some time within the banks, they are faced with the challenge of adapting to the ever-changing risks and methods related to money laundering. In order to provide support for AML decisions, we have formulated an AML conceptual model by following Simon [Simon, H. A. (1977). The new science of management decision. Englewood Cliffs, NJ: Prentice-Hall] decision-making process model. Based on this model, a novel and open multi-agent AML system prototype has been designed and developed. Intelligent agents with their properties of autonomy, reactivity, and proactivity are well suited for dynamic, ill-structured, and complex ML prevention controls. The advanced architecture is able to provide more adaptive, intelligent, and flexible solution for AML. This paper is the first attempt at intelligent agent financial application in the AML domain, with a decision-making/problem-solving process model, an innovative agent-based architecture, and a prototype system.

Domain engineering to ensure flexibility on interaction laws of multi-agent systems

Law enforcement approaches have been proposed to promote dependability in open multi-agent systems. Interaction laws are defined and then enforced to promote predictability. As new software demands and requirements appear, the system and its interaction laws must evolve to support those changes. The purpose of domain engineering is to produce a set of reusable assets for a family of systems, which are then used to build concrete members of the family. Flexibility is the ease with which a system or component can be modified for use in applications other than those for which it was originally designed. In this paper, we discuss how the MLaw infrastructure was designed to support interaction law evolution providing support to produce a set of reusable laws for a family of systems. As an example, we have implemented two customizable applications in the area of electronic negotiation expressed as an open system environment.

Artificial institutions: a model of institutional reality for open multiagent systems

Software agents’ ability to interact within different open systems, designed by different groups, presupposes an agreement on an unambiguous definition of a set of concepts, used to describe the context of the interaction and the communication language the agents can use. Agents’ interactions ought to allow for reliable expectations on the possible evolution of the system; however, in open systems interacting agents may not conform to predefined specifications. A possible solution is to define interaction environments including a normative component, with suitable rules to regulate the behaviour of agents. To tackle this problem we propose an application-independent metamodel of artificial institutions that can be used to define open multiagent systems. In our view an artificial institution is made up by an ontology that models the social context of the interaction, a set of authorizations to act on the institutional context, a set of linguistic conventions for the performance of institutional actions and a system of norms that are necessary to constrain the agents’ actions.

Domain engineering to ensure flexibility on interaction laws of multi-agent systems

Abstract Law enforcement approaches have been proposed to promote dependability in open multi-agent systems. Interaction laws are defined and then enforced to promote predictability. As new software demands and requirements appear, the system and its interaction laws must evolve to support those changes. The purpose of domain engineering is to produce a set of reusable assets for a family of systems, which are then used to build concrete members of the family. Flexibility is the ease with which a system or component can be modified for use in applications other than those for which it was originally designed. In this paper, we discuss how the MLaw infrastructure was designed to support interaction law evolution providing support to produce a set of reusable laws for a family of systems. As an example, we have implemented two customizable applications in the area of electronic negotiation expressed as an open system environment.

Governing multi-agent systems

Abstract In order to cope with the heterogeneity, autonomy and diversity of interests among the different agents in open multi-agent systems, several governance mechanisms have been defined. Governance mechanism enforce the behavior of agents by establishing a set of norms that describe actions that agents are prohibited, permitted or obligated to do. In this paper we present a governance mechanism that enforces not only dialogical actions but also non-dialogical ones. Although several governance mechanisms have been proposed, none of them satisfactorily deals with non-dialogical actions. Our proposed mechanism is based on testimonies provided by agents about the behavior of other agents. The governance mechanism provides decisions pointing out if norms have been violated or if false testimonies have been supplied. The decisions are based not only on testimonies and depositions provided by the agents but also on the agents’ reputations supplied by a reputation system that is part of the mechanism.

An abstract knowledge based approach to diagnosis and recovery of plan failure in multi-agent systems

Open multi-agent systems (MAS) are decentralised and distributed systems that consist of a large number of loosely coupled autonomous agents. In the absence of centralised control they tend to be difficult to manage, especially in an open environment, which is dynamic, complex, distributed and unpredictable. This dynamism and uncertainty in an open environment gives rise to unexpected plan failures. In this paper we present an abstract knowledge based approach for the diagnosis and recovery of plan action failures. Our approach associates a sentinel agent with each problem solving agent in order to monitor the problem solving agent’s interactions. The proposed approach also requires the problem solving agents to be able to report on the status of a plan’s actions. Once an exception is detected the sentinel agents start an investigation of the suspected agents. The sentinel agents collect information about the status of failed plan abstract actions and knowledge about agents’ mental attitudes regarding any failed plan. The sentinel agent then uses this abstract knowledge and the agents’ mental attitudes, to diagnose the underlying cause of the plan failure. The sentinel agent may ask the problem solving agent to retry their failed plan based on the diagnostic result.

Multi-agent based internet search

In this paper, we present a multi-agent system for searching the internet. The search for interesting documents on the internet is becoming more and more difficult. The main problem is not that we do not have the needed information to build or use knowledge, the problem is that we have too much information, mostly irrelevant. A proof of this is that inference engines are largely outperformed by the expansion of the internet and the results of queries are often of very poor quality. To improve the search process, intelligent individual agents were developed. We believe that multi-agent systems can give more accurate results than the individual agents because in a multi-agent system, agents can be specialised in different tasks and can share information. We implemented such an approach using an open multi-agent system containing personal assistants, library agents, filter agents, and search agents. In this paper, we study the models of internet multi-agent systems and propose an architecture to do intelligent web search. The application is based on an AUML protocol (slightly extended) to allow interoperability and yields more accurate results than standard search engines.