Dear Leon,

The idea of commenting the articles of the collections, was not that of modifying. They are peer-reviewed and copyrighted materials, whose contents cannot be altered. Only following a careful edition and peer-review protocol, a new article would eventually be created, which in no case would override the old one. It was a failure by our side, that you could even edit it, due to parallel works in which the blocking mechanisms were temporary shut off. For that reason, I have restored the original François' article and I let below the state os the modified article as you leave it.

Best regards,

José María Díaz Nafría [JDíaz] (talk) 11:32, 29 December 2025 (CET)

State if the article as modified by Leon Zipfel in December 27th 2025

Introduction

There is no single, universally accepted definition of an agent, but rather several valid ones. The term is used in many different fields of study, such as artificial intelligence, system theory and network science. This makes it quite difficult to identify one definitive definition, since each field emphasizes different aspects of what constitutes an agent and defines it according to its specific context. However, by examining these different definitions, it is possible to develop a more general understanding of what the term agent means.

Agent

One of the most general definitions of the term comes from Stuart J. Russell and Peter Norvig. They state in their paper Artificial Intelligence: A Modern Approach that,“An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators” ^[1]. This definition is deliberately broad and depends heavily on how the concept of the environment is specified. Because it is so general, it is fairly easy to depict the idea, as shown in Figure 1, which is based heavly on the dipiction Stuart J. Russell and Peter Norvig used in their paper.

An agent could also be characterized as an active element in a multi-elements system or network.

J. ERCEAU and J. FERBER describe the following types of agents, at different hierarchical levels in the active multi-agents system:

- “reactive agents: these are at the lower levels. They merely dispose of a reduced protocole and communication language and … their abilities rely only on a stimulus/action rule. The reactive agents class include various levels, according to their group-forming ability and capacity to produce global behavior;

- “communicating agents, which possess a complete communication protocole, but whose conversational and behavioral parts are interdependent;

- “rational agents, which possess precise abilities, beliefs and a partial representation of their environment, specially of the other agents within the system;

- “intentional agents, at the highest level, possessing explicit goals, specific plans which allow them to fulfill their goals, as well as the possibility to commit themselves to specific tasks, that they are obliged to carry out, or to contract other agents to execute certain actions”. (1991, p.757-8)

This could be a stimulating description for a model of any society.

More recently, J. FERBER (1999) has given another much more precise definition of an agent:

According to Ferber, an Agent is a virtual or physical entity which:

1) is capable of acting in an environment

2) can communicate directly with other agents

3) is driven by a set of tendencies (in the form of individual objectives or of a satisfaction/survival function which it tries to optimize)

4) possesses resources of its own

5) is capable to perceive its environment (but up to a limited extent)

6) has only a partial representation of this environment (and perhaps none at all)

7) possesses skills and can offer services

8) may be able to reproduce itself

9) whose behavior tends towards satisfying its objectives , taking account of the resources and skills available to it and depending on its perception , its representation and the communication it receives

“Having the properties 1-9) an agent can be considered as an ”intelligent system“(Ibid)

Another influential characterization of intelligent agents is provided by B. HAYES-ROTH in An Architecture for Adaptive Intelligent Systems. "Intelligent agents continuously perform three functions: perception of dynamic conditions in the environment; action to affect conditions in the environment; and reasoning to interpret perceptions, solve problems, draw inferences, and determine actions."^[2] This definition concentrates on the functional coupling of perception, reasoning, and action as the basis of adaptive intelligent behavior.

By contrast, in the previously discussed definition by Jacques Ferber adopts a more structural and property-based perspective. Ferber defines agents as physical or virtual entities characterized by a set of capabilities, including action, communication, goal-oriented behavior, partial environmental representation, and the possession of resources and skills. Within this framework, intelligence is not presupposed but may emerge from the combination of these properties (Ferber, 1999).

These definitions reflect different theoretical emphases: Hayes-Roth’s approach, rooted in artificial intelligence, focuses on internal functional processes underlying intelligent behavior, whereas Ferber’s definition, developed in the context of multi-agent systems, highlights interaction and functional roles within distributed systems.

This example illustrates perfectly how different fields of resarch employ definitions of agents that are precisely adapted to their respective research goals, methodological assumptions, and domains of application.

From the description of J. FERBER, N. SAFFARPOUR (2000, p. 75) deduces the following characteristics of agents

“- Agents are autonomous , i.e. have control over their own actions

- Agents contain some level of intelligence, from fixed rule to learning engine that allows them to adapt to change in the environment

- Agents don't only act reactively, but sometimes also proactively and don't simply act in response to environment , in other words agents are goal oriented

- Agents have social ability, that is they communicate with the user, the system and other agents as required

- Agents may also cooperate with other agents to carry out more complex tasks that those they themselves can handle

- Agents may move from one system to another to access remote recourse or even to meet other agents

- Agents are adaptive, that is change their behavior based on previous experience

While some of these terms may appear ambiguous—such as intelligence or mobility—they remain significant for understanding agents in a general sense.

Conclusion

In conclusion, the concept of an agent should be understood as an analytical abstraction rather than a rigid classification. As emphasized by Stuart J. Russell and Peter Norvig in Artificial Intelligence: A Modern Approach, "The notion of an agent is meant to be a tool for analyzing systems, not an absolute characterization that divides the world into agents and non-agents." ^[3] Whether something is treated as an agent depends on the perspective, purpose, and level of analysis adopted. This flexibility is precisely what makes the agent concept powerful: it allows complex systems to be studied in a structured way without imposing artificial boundaries between agents and non-agents.

IESC talk:AGENT

State if the article as modified by Leon Zipfel in December 27th 2025

Introduction

Agent

Conclusion

See also