Abstract-Agent-oriented software is an established research field. For this reason, it is important to develop comprehensive measures of excellence to evaluate this software. No set of measures defining the overall quality of an agent has been developed to date. Some attempts at evaluating agent quality have addressed certain agent features, like the development process. We believe that agent quality can be determined as a function of well-defined characteristics. Evaluated using appropriate measures, these characteristics will assure an agent's reliability and correct functionality. This paper deals with an important agent feature, namely, autonomy. Autonomy is considered to be the agent's ability to operate independently, without the need for human guidance or the intervention of external elements. The article proposes a set of measures used to evaluate the autonomy of a agent and presents a case study analysing the behaviour of these measures.
Abstract-Despite having well-defined characteristics, software agents do not have a developed set of measures defining their quality. Attempts at evaluating software agent quality have focused on some agent aspects, like the development process, whereas others focusing on the agent as a software product have basically adopted measures associated with other software paradigms, like procedural and object-oriented concepts. Here we propose a set of measures for evaluating software agent pro-activity, the software agent's goal-driven behavioral ability to take the initiative and satisfy its goals.
Abstract. This paper is part of research aimed at determining and evaluating software agent quality considering an agent's distinctive characteristics, like social ability, autonomy, pro-activity, etc. We present a study of the pro-activity characteristic, regarded as the software agent's goal-driven behavioral ability to take the initiative and satisfy its design goals. We establish attributes associated with this characteristic and set out measures enabling its global evaluation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.