Artificial Intelligence + Distributed Systems = Agents
The connection with Wirth's book goes beyond the title, albeit confining the area to modern Artificial Intelligence, and results of recent research are abridged and commented upon in line with new paradigms.
Abstract
The connection with Wirth's book goes beyond the title, albeit confining the area to modern Artificial Intelligence (AI). Whereas thirty years ago, to devise effective programs, it became necessary to enhance the classical algorithmic frame- work with approaches applied to limited and focused subdomains, in the context of broad-band technology and semantic web, applications - running in open, heteroge- neous, dynamic and uncertain environments-current paradigms are not enough, be- cause of the shift from programs to processes. Beside the structure as position paper, to give more weight to some basic assertions, results of recent research are abridged and commented upon in line with new paradigms. Among the conclusions: a) Non- deterministic software is unavoidable; its development entails not just new design principles but new computing paradigms. b) Agent-oriented systems, to be effectual, should merge conventional agent design with approaches employed in advanced dis- tributed systems (where parallelism is intrinsic to the problem, not just a mean to speed up).