A Multi-agent System Framework for Dialogue Games in the Group Decision-Making Context

Abstract

Dialogue games have been applied to various contexts in computer science and artificial intelligence, particularly to define interactions between autonomous software agents. However, in order to implement dialogue games, the developers need to deal with other important details besides what is presented in the model's definition. This is a complex work, mostly when it is expected that the agents' interactions correctly represent a human group behavior. In this work, we present a multi-agent system framework specifically designed to facilitate the implementation of dialogue games under the context of group decision-making in which agents interact as the humans do in face-to-face meetings. The proposed framework, named MAS4GDM, encapsulates the JADE framework and provides a layer that allows developers to easily implement their dialogue models without being concerned with some complex implementation details, such as: the communication model, the agents' life cycle, among others. We ran an experimental evaluation and verified that the proposed framework allows to implement dialogue models in an easier way and abstract the developers from important implementation details that can compromise the application's success.

Modeling a Mobile Group Recommender System for Tourism with Intelligent Agents and Gamification

“…So, each agent will consider the respective tourist's preferences, personality, socio-cultural aspects, mood, intentions, etc., to choose the POI to visit from the list, engaging in a real time conversation with the other agents by using argumentation. The agents argumentation will also be based on the dynamic argumentation model developed in our previous work [23,24], and will use dialogues of different types, such as negotiation and deliberation [25], to propose solutions and reach a final consensus on the list of POI to visit that better suits the group's interests and intentions. We believe this strategy can be helpful for large groups, since the agents automatic dialogues will minimize the time the tourists will need to spend in the system to reach a consensus, and will avoid the confusion inherent to chats of large groups of people, simplifying and making the choice process more organized.…”

Intelligent Systems in Healthcare: An Architecture Proposal

“…Each agent can represent a specific functionality or service, and can communicate with other agents to exchange information and coordinate actions [6]. This architecture allows for the exposure of Intelligent Agents' capabilities through RESTful APIs, with an impact on how MAS are viewed and implemented, making it easier to incorporate agile development techniques and modify how agents are accessed and utilized, resulting in systems that are quicker and more intelligent [21].…”

Semantic Web Services for Multi-Agent Systems Interoperability

“…While in some scenarios these systems directly communicate with each other [9,11], such is not always the case [5,8]. This problem becomes even more complex if the data must be transformed through other processes, such as those provided by services or tools [12], whose…”