Modular Design Patterns for Hybrid Actors

TL;DR

This paper extends a graphical design language for hybrid AI by incorporating actors and interactions, providing a taxonomy and examples relevant to multi-agent and human-agent systems.

Contribution

It introduces an extended taxonomy for distributed hybrid AI systems with actors and interactions, enhancing the existing boxology framework.

Findings

Extended taxonomy for hybrid AI systems with actors

Examples of design patterns in multi-agent and human-agent interactions

Enhanced graphical language for hybrid AI design

Abstract

Recently, a boxology (graphical language) with design patterns for hybrid AI was proposed, combining symbolic and sub-symbolic learning and reasoning. In this paper, we extend this boxology with actors and their interactions. The main contributions of this paper are: 1) an extension of the taxonomy to describe distributed hybrid AI systems with actors and interactions; and 2) showing examples using a few design patterns relevant in multi-agent systems and human-agent interaction.