Computer Science and Engineering
Agents are proliferating on the Web, making it conceivable that their collective reasoning ability might someday be harnessed for robust decision-making. The hope is that massive deliberation power can soon help solve problems that require knowledge, reasoning, and intelligence. Until recently, working individually or in small groups, agents across the Web could barely communicate and could only reason under conditions of severely bounded rationality. Projects such as Agentcities showed that widespread heterogeneous agents could collaborate on specific predefined tasks and provide diverse agent-based services. When the tasks are dynamic, of long duration, and ill defined, however, success requires planning that is continual, distributed, and accounts for the social fabric into which the plans and their execution must fit. The authors discusses distributed planning and societal agents.
Published in IEEE Internet Computing, Volume 7, Issue 1, 2003, pages 72-75.
© 2003 by the Institute of Electrical and Electronics Engineers (IEEE)