The Wikipedia definitions are as follows

Multi-agent systems - A multi-agent system is a computerized system composed of multiple interacting intelligent agents.

Multi-modal interaction - Multimodal interaction provides the user with multiple modes of interacting with a system.

Doesn't providing a user with multiple modes of interacting with a system, assuming all modalities interact with each other to give final output (some sort of fusion mechanism for example), make it a multi-agent system?

If not, what is the difference between multi-modal and multi-agent systems and, monolithic and uni-modal systems?

  • $\begingroup$ analogy: Just because I can either drive with my left hand or right hand, I am still the only one driving $\endgroup$
    – mshlis
    Aug 5, 2019 at 17:32

1 Answer 1


An agent is a concept, which can have slightly different meanings, abilities or instantiations depending on the context. However, given the purpose of this website, I will use and refer to the definition of agent commonly used in artificial intelligence.

An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.

For more details regarding the definition of an agent in AI, see my answer to the question What is an agent in Artificial Intelligence?.

A multi-agent system is a system composed of multiple agents that interact with an environment. See Multi-Agent Systems: A survey (2018) fore a more exhaustive overview of the field.

Multimodal interaction (MI) refers to the interaction with a system (e.g. a computer) using multiple modalities (e.g. speech or gestures). For example, we usually can interact with a laptop using a keyboard and a touchpad (or mouse), so the keyboard and the touchpad are the two different modalities that are used to interact with the computer. MI could thus be considered a sub-field of human-computer interaction.

Conceptually, an agent could be associated with each modality provided by a multimodal system, so a system that provides multimodal interaction could indeed be a multi-agent system. See, for example, A Multi-Agent based Multimodal System Adaptive to the User’s Interaction Context (2011).


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .