Collaborative filters help people make choices based on the opinions of other people. GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles. News reader clients display predicted scores and make it easy for users to rate articles after they read them. Rating servers, called Better Bit Bureaus, gather and disseminate the ratings. The rating servers predict scores based on the heuristic that people who agreed in the past will probably agree again. Users can protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction. The entire architecture is open: alternative software for news clients and Better Bit Bureaus can be developed independently and can interoperate with the components we have developed.

While there are many Web services which help users find things to buy,we know of none which actually try to automate the process of buying and selling. Kasbah is a virtual marketplace on the Web where users create autonomous agents to buy and sell goods on their behalf. Users specify parameters to guide and constrain an agent's overall behavior. A simple prototype has been built to test the viability of this concept.

The Web is less agent-friendly than we might hope. Most information on the Web is presented in loosely structured natural language text with no agent-readable semantics. HTML annotations structure the display of Web pages, but provide virtually no insight into their content. Thus, the designers of intelligent Web agents need to address the following questions: (1) To what extent can an agent understand information published at Web sites? (2) Is the agent's understanding sufficient to provide genuinely useful assistance to users? (3) Is site-specific hand-coding necessary, or can the agent automatically extract information from unfamiliar Web sites? (4) What aspects of the Web facilitate this competence? In this paper we investigate these issues with a case study using the ShopBot. ShopBot is a fullyimplemented, domain-independent comparison-shopping agent. Given the home pages of several on-line stores, ShopBot autonomously learns how to shop at those vendors. After its learning is com...

this article, we focus on the ideas underlying the softbot-based interface.

ion and delegation: Agents can be made extensible and composable in ways that common iconic interface objects cannot. Because we can "communicate" with them, they can share our goals, rather than simply process our commands. They can show us how to do things and tell us what went wrong (Miller and Neches 1987). . Flexibility and opportunism: Because they can be instructed at the level of 16 BRADSHAW goals and strategies, agents can find ways to "work around" unforeseen problems and exploit new opportunities as they help solve problems. . Task orientation: Agents can be designed to take the context of the person's tasks and situation into account as they present information and take action. . Adaptivity: Agents can use learning algorithms to continually improve their behavior by noticing recurrent patterns of actions and events. Toward Agent-Enabled System Architectures In the future, assistant agents at the user interface and resource-managing agents behind the scenes will increas...

Like middle-men in physical commerce, middleagents support the flow of information in electronic commerce, assisting in locating and connecting the ultimate information provider with the ultimate information requester. Many different types of middleagents will be useful in realistic, large, distributed, open multi-agent problem solving systems. These include matchmakers or yellow page agents that process advertisements, blackboard agents that collect requests, and brokers that process both. The behaviors of each type of middle-agent have certain performance characteristics---privacy, robustness, and adaptiveness qualities---that are related to characteristics of the external environment and of the agents themselves. For example, while brokered systems are more vulnerable to certain failures, they are also able to cope more quickly with a rapidly fluctuating agent workforce and meet certain privacy considerations. This paper identifies a spectrum of middle-agents, cha...

Interface agents are semi-intelligent systems which assist users with daily computer-based tasks. Recently, various researchers have proposed a learning approach towards building such agents and some working prototypes have been demonstrated. Such agents learn by `watching over the shoulder' of the user and detecting patterns and regularities in the user's behavior. Despite the successes booked, a major problem with the learning approach is that the agent has to learn from scratch and thus takes some time becoming useful. Secondly, the agent's competence is necessarily limited to actions it has seen the user perform. Collaboration between agents assisting different users can alleviate both of these problems. We present a framework for multiagent collaboration and discuss results of a working prototype, based on learning agents for electronic mail. Introduction Learning interface agents are computer programs that employ machine learning techniques in order to provide assistance to a u...

One category of researchers in artificial life is concerned with modeling and building so-called adaptive autonomous agents. Autonomous agents are systems that inhabit a dynamic, unpredictable environment in which they try to satisfy a set of time-dependent goals or motivations. Agents are said to be adaptive if they improve their competence at dealing with these goals based on experience. Autonomous agents constitute a new approach to the study of artificial intelligence (AI) which is highly inspired by biology, in particular ethology, the study of animal behavior. Research in autonomous agents has brought about a new wave of excitement into the field of AI. This paper reflects on the state of the art of this new approach.

The current exponential growth of the Internet precipitates a need for new tools to help people cope with the volume of information. To complement recent work on creating searchable indexes of the World-Wide Web and systems for filtering incoming e-mail and Usenet news articles, we describe a system which helps users keep abreast of new and interesting information. Every day it presents a selection of interesting web pages. The user evaluates each page, and given this feedback the system adapts and attempts to produce better pages the following day. We present some early results from an AI programming class to whom this was set as a project, and then describe our current implementation. Over the course of 24 days the output of our system was compared to both randomly-selected and human-selected pages. It consistently performed better than the random pages, and was better than the human-selected pages half of the time. Introduction In recent years there has been a well-publicized expl...

Automating routine organizational tasks, such as meeting scheduling, requires a careful balance between the individual (respecting his or her privacy and personal preferences) and the organization (making efficient use of time and other resources). We argue that meeting scheduling is an inherently distributed process, and that negotiating over meetings can be viewed as a distributed search process. Keeping the process tractable requires introducing heuristics to guide distributed schedulers' decisions about what information to exchange and whether or not to propose the same tentative time for several meetings. While we have intuitions about how such heuristics could affect scheduling performance and efficiency, verifying these intuitions requires a more formal model of the meeting schedule problem and process. We present our preliminary work toward this goal, as well as experimental results that validate some of the predictions of our formal model. We also investigate scheduling in ove...