Papers on Intelligent Agents

Publications

Papers on EXPECT

Papers on Planning

Papers on Knowledge Acquisition

Papers on Intelligent Agents

Papers on Ontologies and Problem-Solving Methods

Papers on Proactive Dialogue

Papers on Machine Learning

Papers on Intelligent Agents

Hans Chalupsky, Yolanda Gil, Craig A. Knoblock, Kristina Lerman, Jean Oh, David V. Pynadath, Thomas A. Russ, and Milind Tambe. "Electric Elves: Applying agent technology to support human organizations." Proceedings of the Thirteenth Annual Conference on Innovative Applications of Artificial Intelligence (IAAI'01) Seattle, WA, August 2001. ( PDF file)

Abstract: The operation of a human organization requires dozens of everyday tasks to ensure coherence in organizational activities, to monitor the status of such activities, to gather information relevant to the organization, to keep everyone in the organization informed, etc. Teams of software agents can aid humans in accomplishing these tasks, facilitating the organization's coherent functioning and rapid response to crises, while reducing the burden on humans. Based on this vision, this paper reports on Electric Elves, a system that has been operational, 24/7, at our research institute since June 1, 2000. Tied to individual user workstations, fax machines, voice, mobile devices such as cell phones and palm pilots, Electric Elves has assisted us in routine tasks, such as rescheduling meetings, selecting presenters for research meetings, tracking people's locations, organizing lunch meetings, etc. We discuss the underlying AI technologies that led to the success of Electric Elves, including technologies devoted to agent-human interactions, agent coordination, accessing multiple heterogeneous information sources, dynamic assignment of organizational tasks, and deriving information about organization members. We also report the results of deploying Electric Elves in our own research organization.

Yolanda Gil and Surya Ramachandran. "PHOSPHORUS: A Task-Based Agent Matchmaker". Proceedings of the International Conference on Autonomous Agents (Agents'01) (Short paper) Montreal, Canada, May 2001. ( PDF file)

Abstract: PHOSPHORUS is an agent matchmaking service that exploits domain ontologies, description logic, and a highly declarative language to reason about task-related agent capabilities. PHOSPHORUS uses the EXPECT goal language to represent the tasks that agents are capable of accomplishing, as well as requests to locate agents with a required capability. PHOSPHORUS supports matching through subsumption, reverse subsumption, and several kinds of goal reformulation.