Abstract: The term "agent" has come to be a widely used and abused term. This paper gives a deduction of the term agency, starting from a fundamentally oriented theory framework and ending with an implementation proposal on a generic agent architecture, based on the underlying concepts of science theory.
Originally the term agent is a substitute for canvasser or actor (in latin: agere), meaning somebody who acts upon somebody else’s behalf. Several attempts to define agents have been made., i.e. by Franklin and Graesser, Wooldridge and Jennings, Huhn, Nwana and others. Hot and in cyclic periods u pflaring discussions have divided the researcher society in agency in two extreme poles when it comes to defining the word agent: the hardcore AI society takes the long-standing traditional view that agents are essentially conscious, cognitive entites that have human-like feelings, perceptions, and emotions, using terms from areas like biology or psychology, which do have nothing to do with the subject itself. The other, extremly pragmatically and program-oriented side takes the view of an agent as a software program which does exactly what it's told.
This notion leaves room for almost any program and bears the risk of loosing every distinction towards agency. The truth obviously lies somewhere in between, which is our motivation for a new solution approach in defining agency.
We feel that most definitions of agents have an adhoc character and lack methodological approaches to the definition of agents. To overcome this deficiency we want to separate the discussion about agents, especially learning agents and the environment they live in, into two clearly defined areas: the area of formalized scientific empirical theories and the area of computer science. From the formalized foundations we deduce a generic architecture for agents. The paper closes with a comparison of some traditional definitions with our agent view.
Victor Taratoukhine, Kamal Bechkoum A MULTI-AGENT APPROACH FOR DESIGN CONSISTENCY CHECKING
This research reviews existing methods and techniques addressing the problem of mismatch control in distributed collaborative design. In order to contribute towards a more comprehensive solution a basis for a taxonomy of design mismatches is presented. The paper argues that a multi-agent approach is a more effective, and a promising, way forward towards a comprehensive automatic solution to the problem. An outline multi-agent architecture is proposed. The architecture assumes that the design knowledge is encapsulated within the different members of agent community. Agents are endowed with the capacity of negotiation with one another to ensure that any mismatches are detected and that a solution is proposed. The notions of proactiviness and social ability, which the agents need to exhibit, are central to this work.
Research into the use of knowledge engineering in design has become widely accepted as a fast growing subfield of Artificial Intelligence (AI). Increasing numbers of researchers, and research groups, are active within this emerging subfield. From advocates of “knowledge intensive” CAD/CAM/CAE [1,2] to promoters of broader “intelligent CAD frameworks” [3,4], the common thread is the use of AI tools and techniques to provide automatic and semi-automatic solutions aiming at increasing the “intelligence” of existing CAD/CAM/CAE systems.
The AI technologies used are varied and include expert systems , genetic algorithms and evolution programming , fuzzy logic , multi-agent systems .
It is fair to say though, that design engineers are still skeptical about the ability (or inability) of current intelligent design-support systems. For example, even when endowed with some sort of intelligent behaviour, existing CAD/CAE systems cannot handle several types of inconsistencies that may occur during the design phase. The situation deteriorates if the system is dealing with CAD/CAE data that was generated as part of a distributed collaborative design process.
Mainly due to the complexity of the design process existing solutions tend to approach the problem from a very specific angle. For example, commercial systems such as CATIA (Dassault Systems) and I-DEAS (SDRC) do provide assembly mismatch analysis, but their approaches are more focussed on the analysis of tolerances. Other contributions  are constrained by the number and types of mismatches considered. Often attention is given to a few geometric mismatches only, with very little concern about (say) material or cost considerations.
Moreover, even when the proposed approach is successful in detecting a design anomaly rarely does it suggest a satisfactory way to resolve the problem. In most of the previous work all the design knowledge is centrallised into one unit: the knowledge base . The centralisation of knowledge coupled with the absence of a negotiation mechanism (between all parties involved in the design) makes the process of predicting the impact of any modification an (almost) impossible task.
We re-inforce here the view that a multi-agent approach can tackle many of the problems posed by the centralisation of knowledge into a single Knowledge Base.
None of the aforementioned applications of multi-agent systems is orientated towards dealing with the problem of detecting mismatches that may occur during the integration phase of distributed design. The paper  describes a Intelligent Mismatch Control System (IMCS) which has the potential to detect some of types mismatches. The IMCS implementation is an important step towards a more comprehensive solution but is far from being free from defects. For example, the number and types of mismatches handled by the system is narrowed down to a few geometric mismatches.
The work presented here takes the IMCS’ development one step forward. A new multi-agent architecture is proposed which gives the IMCS the ability to handle issues peculiar to the nature of distributed design. This multi-agent architecture will be at the heart of an intelligent distributed mismatch control system (IDMCS) that aims at ensuring that the overall design is consistent and acceptable to all.
 T. Tomiyama, “Towards knowledge intensive intelligent CAD, ” Preprints of the JSME-ASME Joint Workshop on Design '93-Frontiers in Engineering Design, Tokyo, pp. 46-51, 1993.
 T. Tomiyama, T. Kiriyama, and Y. Umeda, “Towards knowledge intensive engineering. Knowledge Building and Knowledge Sharing,” K. Fuchi and T. Yokoi (eds.), Ohmsha, Ltd. and IOS Press, Tokyo and Amsterdam, pp. 308-316, 1994.
 V. Akman, P.J. ten Hagen, and T. Tomiyama, “A Fundamental and Theoretical Framework for an Intelligent CAD System,” Computer Aided Design Journal, Vol. 22, pp. 352-367, 1990.
 J. Bento, and B. Feijo, “An Agent Based Paradigm for Building Intelligent CAD Systems,” Artificial Intelligence in Engineering Journal, Vol. 11, pp. 231-244, 1997.
 K. Bechkoum, “Intelligent Eletronic Mock-up for Concurrent Design,” Expert Systems with Applications Journal, Vol. 12, pp. 21-36, 1997.
 J. S. Gero, “Adaptive Systems in Designing: New Analogies from Geneticis and developmental Biology, ” in Adaptive Computing in Design and Manufacture, I.Parmee (ed.), Springer, London, pp. 3-12, 1998.
 I. V. Semoushin, V.V. Shishkin, and V. V. Taratoukhine, ”Knowledge-based Network Simulation System,” Proceedings of the 7th International Fuzzy Systems Association Congress, Czech Republic, Prague, pp. 532 – 537, 1997.