Agent-Based Information Gathering

With the proliferation of electronically available information, an additional burden has been placed on the implementors of information gathering (IG) systems. The set of data that represents the best response to a query may be the aggregation of data acquired from distributed, heterogeneous information sources. In such environments, we distinguish between two approaches to the problem of information gathering that may be characterized as distributed processing and distributed problem solving (DPS). The former is characteristic of existing IG systems while the latter is the raison d'etre for Multi-Agent Systems (MAS). We are examining the features of problems that point to the need for a DPS approach, and the benefits of viewing information gathering as distributed problem solving (which subsumes distributed processing). This approach, called Cooperative Information Gathering (CIG), involves concurrent and asynchronous access and composition of associated information spread across a network of information servers by a group of intelligent agents. Top level queries drive the creation of partially elaborated information gathering plans, resulting in the employment of multiple semi-autonomous, cooperative agents for the purpose of achieving goals and subgoals within those plans.

The Agent-Based Information Gathering project documents our efforts to design the next generation of information gathering assitants. Using both single-agent and cooperative versions of the strategy described above, our goal is to design a system capable of effectively searching and utilizing the huge quantities of relevant unformatted information available on the Internet. This work represents the culmonation of many years of effort, integrating technologies developed in several different areas of study research, including planning, information extraction, scheduling and decision making.

The pages below will help describe the current state and eventual goals of our research.

Overview
An overview of our single-agent approach to information gathering.

Example
A walkthrough of our current system's execution.

Related Publications

Lesser, Victor; Horling, Bryan; Klassner, Frank; Raja, Anita; Wagner, Thomas; and Zhang, Shelley. BIG: An Agent for Resource-Bounded Information Gathering and Decision Making. Artificial Intelligence Journal, Special Issue on Internet Information Agents, Volume 118, Number 1-2, Elsevier Science, pp. 197-244. 2000. Also available as UMass Computer Science Technical Report 1998-52

Lesser, Victor; Horling, Bryan; Raja, Anita; Wagner, Thomas; Zhang, Xiaoqin. Resource-Bounded Searches in an Information Marketplace. IEEE Internet Computing: Agents on the Net, Volume 4, Number 2, IEEE Computer Society Publications, pp. 49-57. 2000.

Lesser, V., Horling, B., Klassner, F., Raja, A., Wagner, T., Zhang, S.. Recent Extensions to BIG: A Resource-Bounded Information Gathering Agent. Proceedings of AAAI Workshop on Intelligent Information Systems, Orlando, Florida 1999,UMASS Technical Report 1999-13. 1999.

Victor Lesser, Bryan Horling, Frank Klassner, Anita Raja, Thomas Wagner, and Shelley XQ. Zhang. A Next Generation Information Gathering Agent. Proceedings of the 4th International Conference on Information Systems, Analysis, and Synthesis; in conjunction with the World Multiconference on Systemics, Cybernetics, and Informatics (SCI98). 1998. Also available as UMass Computer Science Tech Report 98-72

Lesser, Victor R., Horling, Bryan, Klassner, Frank, Raja, Anita, Wagner, Thomas A., Zhang, Shelley X.Q.. BIG: A Resource-Bounded Information Gathering Agent. Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98).. 1998. Also available as UMass Computer Science Technical Report 1998-03

Lesser, V.R., Horling, Bryan, Klassner, Frank, Raja, Anita, Wagner, Thomas A. and Zhang, Shelley XQ.. Information Gathering as a Resource Bounded Interpretation Task. UMass Computer Science Technical Report 97-34. 1997.

Oates, T., Nagendra Prasad, M.V., and Lesser, V.. Cooperative Information Gathering: A Distributed Problem-Solving Approach. IEE Proceedings on Software Engineering, Special Issue on Agent-based Systems, Volume 144, Number 1, IEE Proceedings on Software Engineering, Special Issue on Agent-based Systems, pp. 72-88. 1997.

Nagendra, Prasad, M.V., Lesser, V., Lander, S.. Retrieval and Reasoning in Distributed Case Bases. Journal of Visual Communication and Image Representation, Special Issue on Digital Libraries, Volume 7, Number 1, pp. 74-87. 1996.

Zilberstein, S, and Lesser, V. Intelligent Information Gathering for Decision Models. UMASS Technical Report 96-35. 1996.

Decker, Keith, Lesser, Victor, Prasad, Nagendra, and Wagner, Thomas. MACRON: An Architecture for Multi-Agent Cooperative Information Gathering. Proccedings of the CIKM Workshop on Intelligent Information Agents. 1995.