Abstract: The explosive growth of the World Wide Web, and the resulting information overload, has led to a mini-explosion in World Wide Web search engines. This mini-explosion, in turn, led to the development of ProFusion, a meta search engine. Educators, like other users, do not have the time to evaluate multiple search engines to knowledgeably select the best for their uses. Nor do they have the time to submit each query to multiple search engines and wade through the resulting flood of good information, duplicated information, irrelevant information, and missing documents. ProFusion sends user queries to multiple underlying search engines in parallel, retrieves and merges the resulting URLs. It identifies and removes duplicates and creates one relevance-ranked list. If desired, the actual documents can be pre-fetched to remove yet more duplicates and broken links. ProFusion's performance has been compared to the individual search engines and other meta searchers, demonstrating its ability to retrieve more relevant information and present fewer duplicates pages. The system can automatically analyze queries to identify its topic(s) and, based on that analysis, select the most appropriate search engines for the query.

. Adaptation in open, multi-agent information gathering systems is important for several reasons. These reasons include the inability to accurately predict future problem-solving workloads, future changes in existing information requests, future failures and additions of agents and data supply resources, and other future task environment characteristic changes that require system reorganization. We have developed a multi-agent distributed system infrastructure, Retsina (REusable Task Structure-based Intelligent Network Agents) that handles adaptation in an open Internet environment. Adaptation occurs both at the individual agent level as well as at the overall agent organization level. The Retsina system 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 p...

To facilitate the rapid development and open system interoperability of autonomous agents we need to carefully specify and effectively implement various classes of agent behaviors. Our current focus is on the behaviors and underlying architecture of WWW-based autonomous software agents that collect and supply information to humans and other computational agents. This paper discusses a set of architectural building blocks that support the specification of behaviors for these information agents in a way that allows periodic actions, interleaving of planning and execution, and the concurrent activation of multiple behaviors with asynchronous components. We present an initial set of information agent behaviors, including responding to repetitive queries, monitoring information sources, advertising capabilities, and self cloning. We have implemented and tested these behaviors on the WWW in the context of WAR-REN, an open multi-agent organization for financial portfolio management.

This paper investigates the problem of automatically learning declarative models of information sources available on the Internet. We report on ILA, a domain-independent program that learns the meaning of external information by explaining it in terms of internal categories. In our experiments, ILA starts with knowledge of local faculty members, and is able to learn models of the Internet service whois and of the personnel directories available at Berkeley, Brown, Caltech, Cornell, Rice, Rutgers, and UC1, averaging fewer than 40 queries per information source. ILA's hypothesis language is compositions of first-order predicates, and its bias is compactly encoded as a determination. We analyze ILA's sample complexity both within the Valiant model, and using a probabilistic model specifically tailored to ILA. 1

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.

We propose an agent-based framework for assisting and simplifying person-to-person communication for information gathering tasks. As an example, we focus on locating experts for any specified topic. In our approach, the informal person-to-person networks that exist within an organization are used to "referral chain" requests for expertise. User-agents help automate this process. The agents generate referrals by analyzing records of email communication patterns. Simulation results show that the higher responsiveness of an agent-based system can be effectively traded for the higher accuracy of a completely manual approach. Furthermore, preliminary experience with a group of users on a prototype system has shown that useful automatic referrals can be found in practice. Our experience with actual users has also shown that privacy concerns are central to the successful deployment of personal agents: an advanced agent-based system will therefore need to reason about issues involving trust an...

The explosive growth of the Web has made intelligent software assistants increasingly necessary for ordinary computer users. Both traditional approaches -- search engines, hierarchical indices -- and intelligent software agents require significant amounts of human effort to keep up with the Web. As an alternative, we investigate the problem of automatically learning to interact with information sources on the Internet. We report on ShopBot and ILA, two implemented agents that learn to use such resources. ShopBot learns how to extract information from online vendors using only minimal knowledge about product domains. Given the home pages of several online stores, ShopBot autonomously learns how to shop at those vendors. After its learning is complete, ShopBot is able to speedily visit over a dozen software stores and CD vendors, extract product information, and summarize the results for the user. ILA learns to translate information from Internet sources into its own internal concept...

Current specialized planners for query processing are designed to work in local, reliable, and predictable environments. However, a number of problems arise in gathering information from large networks of distributed information. In this environment, the same information may reside in multiple places, actions can be executed in parallel to exploit distributed resources, new goals come into the system during execution, actions may fail due to problems with remote databases or networks, and sensing may need to be interleaved with planning in order to formulate efficient queries. Wehavedeveloped a planner called Sage that addresses the issues that arise in this environment. This system integrates previous work on planning, execution, replanning, and sensing and extends this work to support simultaneous and interleaved planning and execution. Sage has been applied to the problem of information gathering to provide a flexible and efficient system for integrating heterog...

Many real-world planning problems require generating plans that maximize the parallelism inherentina problem. There are a number of partial-order planners that generate such plans# however, in most of these planners it is unclear under what conditions the resulting plans will be correct and whether the planner can even find a plan if one exists. This paper identifies the underlying assumptions about when a partial plan can be executed in parallel, defines the classes of parallel plans that can be generated by different partial-order planners, and describes the changes required to turn ucpop into a parallel execution planner. In addition, we describe how this planner can be applied to the problem of query access planning, where parallel execution produces substantial reductions in overall execution time.

This paper presents our first step towards agent-oriented software engineering, focusing on the area of coordinated multi-agent systems. In multi-agent systems, the interactions between the agents are crucial in determining the effectiveness of the system. Hence the adoption of an appropriate coordination mechanism is pivotal in the design of multi-agent system architectures. This paper does not focus on agent theory, rather on the development of an agent-oriented software engineering methodology, collaboration architectures and design patterns for collaboration. A catalog of coordination patterns inherent in multi-agent architectures is presented. Such patterns may be utilized in the architectural design for multiagent systems, allowing researchers and practitioners to improve the integrability and reusability properties of their systems.