Maxime Morge

The ArguGRID Platform: An Overview

The ArguGRID project aims at supporting service selection and composition in distributed environments, including the Grid and Service-oriented architectures, by means of argumentative agents, an agent environment, a service-composition environment, Peer-to-Peer technology and Grid middleware. Agents are argumentative in that they use argumentation-based decision-making and argumentation-supported negotiation of services and contracts. The integration of all technologies gives rise to the overall ArguGRID platform. In this paper we outline the main components and the overall functionalities of the ARGUGRID platform.

The Hedgehog and the Fox

In this paper, we present a decision support system which is built upon an argumentation framework for practical reasoning. A logic language is used as a concrete data structure for holding statements representing knowledge, goals, and decisions. Different priorities are attached to these items, corresponding to the probability of the knowledge, the preferences between goals, and the expected utilities of decisions. These concrete data structures consist of information providing the backbone of arguments. Due to the abductive nature of practical reasoning, arguments are built by reasoning backwards, and possibly by making suppositions over missing information. Moreover, arguments are defined as tree-like structures. In this way, our computer system, implemented in Prolog, suggests some solutions and provides an interactive and intelligible explanation of this choice.

A Negotiation Support System based on a Multi-agent System: specificity and preference relations on arguments

In this paper, we propose a Negotiation Support System based on a Multi-agent System. Each agent assists a user in multi-criteria decision making and negotiates according to this decision-modelling with other agents, each of them representing a user. Moreover agents assist users in the debate to negotiate a joint representation of the problem and automatically justify proposals with this joint representation.

A Virtual Selling Agent which is Proactive and Adaptive

In this paper, we claim that the online selling process can be improved if the experience of the customer is closer to the one in a retailing store. For this purpose, we aim at providing a virtual selling agent that is proactive and adaptive. Our proactive dialogical agent initiates the dialogue, uses marketing strategies and drives the inquiring process for collecting information in order to make relevant proposals. Moreover, our virtual seller is adaptive since she is able to adjust her behaviour according to the buyer profile.

Assumption-based argumentation for the minimal concession strategy

Several recent works in the area of Artificial Intelligence focus on computational models of argumentation-based negotiation. However, even if computational models of arguments are used to encompass the reasoning of interacting agents, this logical approach does not come with an effective strategy for agents engaged in negotiations. In this paper we propose a realisation of the Minimal Concession (MC) strategy which has been theoretically validated. The main contribution of this paper is the integration of this intelligent strategy in a practical application by means of assumption-based argumentation. We claim here that the outcome of negotiations, which are guaranteed to terminate, is an optimal agreement (when possible) if the agents adopt the MC strategy.

Collective decision-making process to compose divergent interests and perspectives

We propose in this paper DIAL, a framework for inter-agents dialogue, which formalize a collective decision-making process to compose divergent interests and perspectives. This framework bounds a dialectics system in which argumentative agents play and arbitrate to reach an agreement. For this purpose, we propose an argumentation-based reasoning to manage the conflicts between arguments having different strengths for different agents. Moreover, we propose a model of argumentative agents which justify the hypothesis to which they commit and take into account the commitments of their interlocutors according to their reputations. In the scope of our dialectics system, a third agent is responsible of the final decision outcome which is taken by resolving the conflict between two players according to their competences and the advanced arguments.

Privacy-Preserving Strategy for Negotiating Stable, Equitable and Optimal Matchings

The assignment problem has a wide variety of applications and in particular, it can be applied to any two-sided market. In this paper, we propose a multi-agent framework to distributively solve this kind of assignment problems, by providing agents which negotiate with respect to their preferences. We present here a realisation of the minimal concession strategy. Our realisation of the minimal concession strategy has useful properties: it preserves the privacy and improves the optimality of the solution and the equity amongst the partners.

Towards a dialectical approach for conversational agents in selling situations

The use of virtual agents to intelligently interface with online customers of e-commerce businesses is remarkably increasing. Most of these virtual agents are designed to assist online customers while searching for information related to a specific product or service, while few agents are intended for promoting and selling a product or a service. Within the later type, our aim is to provide proactive agents that recommend a specific item and justify this recommendation to a customer based on his purchases history and his needs. In this paper, we propose a dialectical argumentation approach that would allow virtual agents that have sales goals to trigger persuasions with e-commerces customers. Then, we illustrate the proposed idea through its integration with an example from real-life. Categories and Subject Descriptors I.2.11 [Artificial Intelligence:] Intelligent Agents. General Terms: Algorithms.

Computing Argumentation for Decision Making in Legal Disputes

In this paper, we present a decision support system for lawyers. This system is built upon an argumentation framework for decision making. A logic language is used as a concrete data structure for holding the statements like knowledge, goals, and decisions. Different priorities are attached to these items corresponding to the uncertainty of the knowledge about the circumstances, the lawyers preferences, and the expected utilities of sentences. These concrete data structures consist of information providing the backbone of arguments. Due to the abductive nature of practical reasoning, arguments are built by reasoning backwards, and possibly by making suppositions over missing information. Moreover, arguments are defined as tree-like structures. In this way, our computer system, implemented in Prolog, suggests some actions and provides an interactive and intelligible explanation of this solution.

A Virtual Selling Agent which is Proactive and Adaptive: Demonstration

In this demonstration, we bring the online selling process closer to the customer experience in a retailing store. For this purpose, we demonstrate a virtual selling agent that is proactive and adaptive. Our proactive dialogical agent initiates the dialogue and drives the inquiring process for collecting information in order to make relevant proposals. Moreover, we will see that our virtual seller is adaptive since she is able to adjust her behaviour according to the buyer profile.