In this paper we discuss a number of previously unaddressed issues that arise in automated negotiation among self-interested agents whose rationality is bounded by computational complexity. These issues are presented in the context of iterative task allocation negotiations. First, the reasons why such agents need to be able to choose the stage and level of commitment dynamically are identified. A protocol that allows such choices through conditional commitment breaking penalties is presented. Next, the implications of bounded rationality are analyzed. Several tradeoffs between allocated computation and negotiation benefits and risk are enumerated, and the necessity of explicit local deliberation control is substantiated. Techniques for linking negotiation items and multiagent contracts are presented as methods for escaping local optima in the task allocation process. Implementing both methods among self-interested bounded rational agents is discussed. Finally, the ...

We are investigating techniques for developing distributed and adaptive collections of agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate a user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the agents does not remain in the user's head but it is explicitly represented and supported through agent collaboration. In this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for constructing agents. We call this reusable multi-agent computational infrastructure RETSINA (Reusable Task Structure-based Intelligent Network Agents). It has three types of agents. Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide syste...

This paper analyzes coalitions among self-interested agents that need to solve combinatorial optimization problems to operate e ciently in the world. By colluding (coordinating their actions by solving a joint optimization prob-lem) the agents can sometimes save costs compared to operating individually. A model of bounded rationality is adopted where computation resources are costly. It is not worthwhile solving the problems optimally: solution quality is decision-theoretically traded o against computation cost. A normative, application- and protocol-independent theory of coalitions among bounded-rational agents is devised. The optimal coalition structure and its stability are signi cantly a ected by the agents ' algorithms ' performance pro les and the cost of computation. This relationship is rst analyzed theoretically. Then a domain classi cation including rational and bounded-rational agents is in-troduced. Experimental results are presented in vehicle routing with real data from ve dispatch centers. This problem is NP-complete and the instances are so large that|with current technology|any agent's rationality is bounded by computational complexity. 1

Abstract not found

A Dissertation Presented by TUOMAS W. SANDHOLM

With the vast number of information resources available today, a critical problem is how to locatc retrieve and process information. It is impracticaJ to build a single unified system that combines all of these information resources. A more modular approach is to build specialized information agents where each agent provides access to a subset of these resources and can serve as an information source to other agents. In this paper wc present the architecture of the individual information agents and describe how this architecture supports a network of cooperating information agents. Wc describe how these information agents represent their knowlcdgc communicate with other agcnts dynamicaJly construct information rctricvaJ plans and learn about other agents to improve their accuracy and efficiency. Wc have aJrcady built a smaJl network of agents that have these capabilities and provide access to information for logistics planning.

With the vast number of information resources available today, a critical problem is how to locate, retrieve and process information. It would be impractical to build a single unified system that combines all of these information resources. A more promising approach is to build specialized information retrieval agents that provide access to a subset of the information resources and can send requests to other information retrieval agents when appropriate. In this paper we present the architecture of the individual information retrieval agents and describe how this architecture supports a network of cooperating information agents. We describe how these information agents represent their knowledge, communicate with other agents, dynamically construct information retrieval plans, and learn about other agents to improve efficiency. We have already built a small network of agents that have these capabilities and provide access to information for transportation planning.

this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents

In multiagent systems, an agent does not usually have complete information about the preferences and decision making processes of other agents. This might prevent the agents from making coordinated choices, purely due to their ignorance of what others want. This paper describes the integration of a learning module into a communication-intensive negotiating agent architecture. The learning module gives the agents the ability to learn about other agents' preferences via past interactions. Over time, the agents can incrementally update their models of other agents' preferences and use them to make better coordinated decisions. Combining both communication and learning, as two complement knowledge acquisition methods, helps to reduce the amount of communication needed on average, and is justified in situations where communication is computationally costly or simply not desirable (e.g. to preserve the individual privacy). Introduction Multiagent systems are networks of loosely-coupled comp...

Most existing Web search tools work only with individual users and do not help a user benefit from previous search experiences of others. In this paper, we present the Collaborative Spider, a multi-agent system designed to provide post-retrieval analysis and enable across-user collaboration in Web search and mining. This system allows the user to annotate search sessions and share them with other users. We also report a user study designed to evaluate the effectiveness of this system. Our experimental findings show that subjects' search performance was degraded, compared to individual search scenarios in which users had no access to previous searches, when they had access to a limited number (e.g., 1 or 2) of earlier search sessions done by other users. However, search performance improved significantly when subjects had access to more search sessions. This indicates that gain from collaboration through collaborative Web searching and analysis does not outweigh the overhead of browsing and comprehending other users' past searches until a certain number of shared sessions have been reached. In this paper, we also catalog and analyze several different types of user collaboration behavior observed in the context of Web mining. D 2002 Elsevier Science B.V. All rights reserved.