Plans, behaviors, and generativity

Ian D Horswill*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Contemporary agent architectures combine deliberative and reactive components in a tiered structure. The reasoning behind this is that reactive systems provide good response time, while deliberative systems provide long-term planning, and more importantly, generativity. In this talk, I will argue that the reactive/deliberative distinction is a false dichotomy, and that, consequently, the rigidity of tiered architectures is actually counter-productive. I will then try to outline a space of alternative architectures, and give examples from working systems.

Original languageEnglish (US)
Title of host publicationIntelligent Agent Architectures
Subtitle of host publicationCombining the Strengths of Software Engineering and Cognitive Systems - Papers from the AAAI-04 Workshop, Technical Report
Number of pages1
StatePublished - Dec 1 2004
Event19th National Conference on Artificial Intelligence - San Jose, CA, United States
Duration: Jul 25 2004Jul 26 2004


Other19th National Conference on Artificial Intelligence
Country/TerritoryUnited States
CitySan Jose, CA

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'Plans, behaviors, and generativity'. Together they form a unique fingerprint.

Cite this