A plug-in architecture for generating collaborative agent responses

ABSTRACT

We describe an implemented architecture for programming the responses of collaborative interface agents out of easily composable and reusable plug-in components, and discuss the underlying theoretical and practical issues. The power of the architecture comes primarily from a rich representation of collaborative discourse state, which includes a focus stack and plan tree. The architecture also provides a useful separation between the principles and preferences underlying an agent's behavior. We illustrate the use of plug-ins in a complex tutoring agent, which includes plug-ins that diagnose incorrect actions and explain why a step needs to be done. Plug-ins are part of the COLLAGEN agent-building middleware, which has been used by a number of researchers in addition to its developers.

REFERENCES

• 1: R. Bergmann and A. Kott. Integrating planning, scheduling and execution in dynamic and uncertain environments. AAAI Tech. Report WS-98-02
• 2: B. Cheikes and A. Gertner, Teaching to Plan and Planning to Teach in an Embedded Training System. In Proc. 10th Int. Conf. on Artificial Intelligence in Education, pages 398--409, San Antonio, TX, May 2001
• 3: Jim R. Davies , Abigail S. Gertner , Neal Lesh , Charles Rich , Candace L. Sidner , Jeff Rickel, Incorporating tutorial strategies into an intelligent assistant, Proceedings of the 6th international conference on Intelligent user interfaces, p.53-56, January 14-17, 2001, Santa Fe, New Mexico, United States [doi>10.1145/359784.360102]
• 4: Elyon DeKoven , David V. Keyson , Adinda Freudenthal, Designing collaboration in consumer products, CHI '01 extended abstracts on Human factors in computing systems, March 31-April 05, 2001, Seattle, Washington [doi>10.1145/634067.634184]
• 5: Barbara J. Grosz , Candace L. Sidner, Attention, intentions, and the structure of discourse, Computational Linguistics, v.12 n.3, p.175-204, July-September 1986
• 6: Dan Gruen , Candy Sidner , Carolyn Boettner , Charles Rich, A collaborative assistant for email, CHI '99 extended abstracts on Human factors in computing systems, May 15-20, 1999, Pittsburgh, Pennsylvania [doi>10.1145/632716.632839]
• 7: John E. Laird , Allen Newell , Paul S. Rosenbloom, SOAR: an architecture for general intelligence, Artificial Intelligence, v.33 n.1, p.1-64, Sept. 1987 [doi>10.1016/0004-3702(87)90050-6]
• 8: Neal Lesh , Charles Rich , Candace L. Sidner, Using plan recognition in human-computer collaboration, Proceedings of the seventh international conference on User modeling, p.23-32, June 1999, Banff, Canada
• 9: Neal Lesh , Charles Rich , Candace L. Sidner, Collaborating with Focused and Unfocused Users under Imperfect Communication, Proceedings of the 8th International Conference on User Modeling 2001, p.64-73, July 13-17, 2001
• 10: Karen E. Lochbaum, A collaborative planning model of intentional structure, Computational Linguistics, v.24 n.4, p.525-572, December 1998
• 11: Charles Rich , Candace L. Sidner, COLLAGEN: A Collaboration Manager for Software Interface Agents, User Modeling and User-Adapted Interaction, v.8 n.3-4, p.315-350, 1998 [doi>10.1023/A:1008204020038]
• 12: Charles Rich , Candace L. Sidner , Neal Lesh, Collagen: applying collaborative discourse theory to human-computer interaction, AI Magazine, v.22 n.4, p.15-25, Winter 2001
• 13: Jeff Rickel , W. Lewis Johnson, Task-oriented collaboration with embodied agents in virtual worlds, Embodied conversational agents, MIT Press, Cambridge, MA, 2001
• 14: J. Rickel, N. Lesh, C. Rich, C. Sidner, and A. Gertner. Building a bridge between intelligent tutoring and collaborative dialogue systems. In Proc. 10th Int. Conf. on Artificial Intelligence in Education, pages 592--594, San Antonio, TX, May 2001
• 15: Jeff Rickel , Neal Lesh , Charles Rich , Candace L. Sidner , Abigail S. Gertner, Collaborative Discourse Theory as a Foundation for Tutorial Dialogue, Proceedings of the 6th International Conference on Intelligent Tutoring Systems, p.542-551, June 02-07, 2002
• 16: Candace L. Sidner, An artificial discourse language for collaborative negotiation, Proceedings of the twelfth national conference on Artificial intelligence (vol. 1), p.814-819, October 1994, Seattle, Washington, United States
• 17: M. Tambe. Towards flexible teamwork. J. of Artificial Intelligence Research, 7:83--124, 1997
• 18: R. M. Young, J. Moore, and M. Pollack. Towards a principled representation for discourse plans. In Proc. 16th Annual Conf. of the Cognitive Science Society, pages 946--951, Hillsdale, NJ, 1994

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Algorithms, Design

Keywords:
action selection and planning, agent architectures, conversational agents, interface agents