Appointment scheduling is a problem faced daily by many individuals and organizations. Cooperating agent systems have been developed to partially automate this task. In order to extend the circle of participants as far as possible we advocate the use of natural language transmitted by e-mail. We describe Cosma, a fully implemented German language server for existing appointment scheduling agent systems. Cosma can cope with multiple dialogues in parallel, and accounts for differences in dialogue behaviour between human and machine agents. NL coverage of the sublanguage is achieved through both corpusbased grammar development and the use of message extraction techniques. 1

A framework for designing a multiagent system (MAS) in which agents are capable of coordinating their activities in routine, familiar, and unfamiliar situations is proposed. This framework is based on the skills, rules and knowledge (S-R-K) taxonomy of Rasmussen. Thus, the proposed framework should allow agents to prefer the lower skill-based and rule-based levels rather than the higher knowledge-based level because it is generally easier to obtain and maintain coordination between agents in routine and familiar situations than in unfamiliar situations. The framework should also support each of the three levels because complex tasks combined with complex interactions require all levels. To permit agents to rely on low levels, a suggestions is developed: agents are provided with social laws so as to guarantee coordination between agents and minimize the need for calling a central coordinator or for engaging in negotiation which requires intense communication. Finally, implemen...

Achieving effective cooperation in a multi-agent system is a difficult problem for a number of reasons such as limited and possiblyout-dated views of activities of other agents and uncertainty about the outcomes of interacting non-local tasks. In this paper, we present a learning system called COLLAGE, that endows the agents with the capability to learn how to choose the most appropriate coordination strategy from a set of available coordination strategies. COLLAGE relies on meta-level information about agents' problem solving situationsto guide them towards a suitable choice for a coordination strategy. We present empirical results that strongly indicate the effectiveness of the learning algorithm. Keywords: Multi-agent Systems, Coordination, Learning 1 Introduction Coordination is the process of effectively managing interdependencies between activities distributed across agents so as to derive maximum benefit from them[21, 6]. Based on structure and uncertainty in their environmen...

Most extant knowledge management systems are constrained by their overly rational, static and acontextual view of knowledge. Effectiveness of such systems is constrained by the rapid and discontinuous change that characterizes new organizational environments. The prevailing knowledge management paradigm limits itself by its emphasis on convergence and consensus-oriented processing of information. Strategy experts have underscored that the focus of organizational knowledge management should shift from `prediction of future' [that cannot be computed] to `anticipation of surprise.' Such systems may be enabled by leveraging the divergent interpretations of information based upon the meaning-making capability of human beings. By underscoring the need for synergy between innovation and creativity of humans and the advanced capabilities of new information technologies, this article advances current thinking about knowledge management.

. The problem of modelling air missions is part of a larger problem - simulating possible war-like scenarios in the air, sea, and on land. In modelling such military systems one is required to model the behaviour of various actors and the resources that are available to them. One aspect of this problem is the modelling of a group of actors as a team and then modelling the coordinated behaviour of such a team to achieve a joint goal. In the domain of air mission modelling the actors are pilots who control aircraft and their behaviour is referred to as tactics. In this paper we present the approach we adopted in modelling teams and team tactics as part of the development of the Smart Whole AiR Mission Model (SWARMM) for the Air Operations Division of the Australian Defence Science and Technology Organization. In our approach teams are composed of sub-teams and adopt organizational structures. Such structures define the responsibilities of the sub-teams towards the mission to be achieved...

Carrying out distributed business processes over networks is rapidly shifting the nature of application architectures from the simple command and control client-server model to complex peer-to-peer models supporting dynamic patterns of social interaction and behavior among autonomous, proactive, goal oriented agents. Trusting agents to autonomously make decisions and execute actions on behalf of humans, as part of global business processes, requires both understanding and modeling of the social laws that govern collective behavior and a practically useful operationalization of the models into agent programming tools. In this paper we present a solution to these problems based on a representation of obliged and forbidden behavior in an organizational framework, together with an inference method that also decides which obligations to break in conflicting situations. These are integrated into an operational, practically useful agent development language that covers the spectrum from the d...

The rapid growth in research and development of agentbased software systems has led to concerns about how human users will control the activities of teams of agents that must actively collaborate. We believe that practical multi-agent systems developed will often be comprised of small teams of heterogeneous agents, under direct supervision by users acting as “team leaders”. We are now developing an environment for investigating approaches to controlling small to medium-sized groups of agents as coordinated teams. This environment will be used to explore mixed-initiative approaches to planning for the activities of agent teams, and managing them during execution. Our approach arises out of a longstanding interest in mixed-initiative planning systems [5]. In this paper, we discuss our approach to mixedinitiative agent team management, some representational issues involved in identifying compatible agent team members and the capabilities needed to monitor team execution.

this paper, we present a learning algorithm that endows agents with the capability to choose a suitable subset of the coordination mechanisms based on the present problem solving situation. The rest of the paper is organized as follows. Section 2 discusses the coordination mechanisms in GPGP. Section 3 introduces our algorithm for situation-specific coordination. We then present a few early experiments in Section 4 and conclude. 2 Coordination in GPGP

The first wave of agent implementation toolkits focussed mostly on providing APIs for agent communication. We believe that new toolkits should focus on the public dissemination of complete agent architectures that provide significant value over building software agents from scratch. DECAF (Distributed, Environment Centered Agent Framework) is a software toolkit for the rapid design, development, and execution of “intelligent ” agents to achieve solutions in complex software systems. DECAF is based on the premise that execution of the actions required to accomplish a task specified by an agent program is similar to a traditional operating system executing a sequence of user requests. In the same fashion that an operating system provides an environment for the execution of a user request, an agent framework provides the needed environment for the execution of agent actions. The agent environment includes the ability to communicate with other agents, efficiently maintain the current state of an executing agent, and select an execution path from a set of possible execution paths so as to support persistent, flexible, and robust actions. From a research community perspective, DECAF provides a modular platform for evaluating and disseminating results in agent architectures, including communication, planning,

a handbook of organizational processes