In a multi-agent environment, where self-motivated agents try to pursue their own goals, cooperation cannot be taken for granted. Cooperation must be planned for and achieved through communication and negotiation. We present a logical model of the mental states of the agents based on a representation of their beliefs, desires, intentions, and goals. We present argumentation as an iterative process emerging from exchanges among agents to persuade each other and bring about a change in intentions. We look at argumentation as a mechanism for achieving cooperation and agreements. Using categories identified from human multi-agent negotiation, we demonstrate how the logic can be used to specify argument formulation and evaluation. We also illustrate how the developed logic can be used to describe different types of agents. Furthermore, we present a general Automated Negotiation Agent which we implemented, based on the logical model. Using this system, a user can analyze and explore differe...

Recent years are seeing an increasing need for on-line monitoring of teams of cooperating agents, e.g., for visualization, or performance tracking. However, in monitoring deployed teams, we often cannot rely on the agents to always communicate their state to the monitoring system. This paper presents

This paper studies argumentation-based dialogues between agents. It defines a set of locutions by which agents can trade arguments, a set of agent attitudes which relate what arguments an agent can build and what locutions it can make, and a set of protocols by which dialogues can be carried out. The paper then considers some properties of dialogues under the protocols, in particular termination and complexity, and shows how these relate to the agent attitudes.

People often act together with a shared purpose; they collaborate on a group action or activity. An increasing number of computer applications also require collaboration among various systems and users. The plans for such collaborative activities must be formed with others, not in isolation. Groups may persist over long periods of time (as do orchestras, sports teams, and systems administration groups), form spontaneously for a single group activity (as when a group forms for a programming project), or come together repeatedly (as do surgical teams and airline crews). A major challenge for researchers in Artificial Intelligence is to determine ways to construct computer systems that are able to act effectively as collaborative team members. Collaborative activities require more than the sum of individual plans. Participants must form commitments not only to the group action itself, but also to the activities of other participants that are in service of this group activity. Gro...

This paper studies argumentation-based dialogues between agents. It defines a set of locutions by which agents can trade arguments, a set of agent attitudes which relate what arguments an agent can build and what locutions it can make, and a set of protocols by which dialogues can be carried out. The paper then considers some properties of dialogues under the protocols, in particular termination, dialogue outcomes, and complexity, and shows how these relate to the agent attitudes.

The growing need for individually motivated agents to work collaboratively to satisfy shared goals has made it increasingly important to design agents that can make intelligent decisions in the context of commitments to group activities. Agents need to reconcile their intentions to do group-related actions with other, conflicting actions. We describe the SPIRE experimental system which allows the process of intention reconciliation in team contexts to be simulated and studied. We define a measure of social consciousness, discuss its incorporation into the SPIRE system, and present several experiments that investigate the interaction in decision-making of measures of group and individual good. In particular, we investigate the effect of infinite and limited time horizons, different task densities, and varying levels of social consciousness on the utility of the group and the individuals it comprises. A key finding is that an intermediate level of social consciousness yields better results than an extreme commitment. We suggest preliminary principles for designers of collaborative agents based on the results.

Recent years are seeing an increasing need for on-line monitoring of deployed distributed teams of cooperating agents, e.g., for visualization, or performance tracking. However, in deployed systems, we often cannot rely on the agents to communicate their state to the monitoring system: (a) we rarely can change the behavior of already-deployed agents to communicate the required information (e.g., in legacy or proprietary systems); (b) different monitoring goals require different information to be communicated (e.g., agents ’ beliefs vs. plans); and (c) communications may be expensive, unreliable, or insecure. This paper presents a non-intrusive approach based on plan-recognition, in which the monitored agents’ state is inferred from observations of their routine actions. In particular, we focus on inference of the team state based on its observed routine communications, exchanged as part of coordinated task execution. The paper includes the following key novel contributions: (i) a linear time probabilistic plan-recognition algorithm, well-suited for processing communications as observations; (ii) an approach to exploiting general knowledge of teamwork to predict agent responses during normal execution, to reduce monitoring uncertainty; and (iii) a monitoring algorithm that trades expressivity for scalability, representing only certain useful monitoring hypotheses, but allowing for any number of agents and their different activities, to be represented in a single coherent entity. Our empirical evaluation illustrates that monitoring based on observed routine communications enables significant monitoring accuracy, while not being intrusive. The results also demonstrate a key lesson: A combination of complementary low-quality techniques is cheaper, and better, than a single, highly-optimized monitoring approach. 1.

individual has the collective expertise, information, or resources required for the eective completion or performance of a task. This paper describes a prototype, implemented in the RETSINA multi-agent infrastructure, in which agents interact with each other via capability-based and team-oriented coordination. We propose a model of team-oriented agent coordination that is based on the joint intentions theory, so that agents can communicate their intended commitments to each other. Team-oriented agents communicate partial descriptions of the context in which a mission must be executed and the resources to do so via data structures that are analogous to the SharedPlans recipe. The agents then proceed, in a process reminiscent of SharedPlans partial plan re- nement, to re ne and revise their understanding of the mission context, via both team-oriented and capability-based coordination with other RETSINA agents, while executing their mission. The partial plan re nement behavior is made possible through the RETSINA Agent Architecture, which interleaves HTN planning and process execution. We enhance the above models of teamwork by adding our own characterizations of checkpoints, role and subgoal relations in software agent teamwork, and show how the software agents can acquire this information from their operating environment during plan execution time. Such enhancements create a scalable team-oriented multi-agent system architecture, in which team coordination strategies can be implemented in a general and domain-independent way.

Agents in dynamic multi-agent environments must monitor their peers to execute individual and group plans. A key open question is how much monitoring of other agents' states is required to be effective: The Monitoring Selectivity Problem. We investigate this question in the context of detecting failures in teams of cooperating agents, via Socially-Attentive Monitoring, which focuses on monitoring for failures in the social relationships between the agents. We empirically and analytically explore a family of socially-attentive teamwork monitoring algorithms in two dynamic, complex, multi-agent domains, under varying conditions of task distribution and uncertainty. We show that a centralized scheme using a complex algorithm trades correctness for completeness and requires monitoring all teammates. In contrast, a simple distributed teamwork monitoring algorithm results in correct and complete detection of teamwork failures, despite relying on limited, uncertain knowledge, and monitoring only key agents in a team. In addition, we report on the design of a socially-attentive monitoring system and demonstrate its generality in monitoring several coordination relationships, diagnosing detected failures, and both on-line and off-line applications.

Proactive information delivery is critical to achieving effective teamwork. However, existing theories do not adequately address proactive information delivery. This paper presents a formal framework for proactive information delivery in agent teamwork. First, the concept of information need is introduced. Second, a new modal operator, InfoNeed is used to represent information needs. The properties of the InfoNeed operator and its relationships to other mental modal operators are examined, four types of information needs are formally identified, and axioms for anticipating the information needs of other agents are proposed and justified. Third, the axiom characterizing chains of helpful behavior in large agent teams is given. Fourth, the semantics for two proactive communicative acts (ProInform and 3PTSubscribe) is given using a reformulation of the Cohen-Levesque semantics for communicative acts in terms of the SharedPlans formalism of Grosz and Kraus. The work in this paper not only provides a better understanding of the underlying assumptions required to justify proactive information delivery behavior, but also provides a coherent basis for the specification and design of agent teams with proactive information delivery capabilities.