Evaluation Mechanism of Collective Intelligence for Heterogeneous Agents Group

TL;DR

This paper introduces an improved evaluation method for measuring collective intelligence in heterogeneous agent groups, analyzing how factors like composition and complexity influence group performance.

Contribution

It extends the existing AUIT to heterogeneous groups, providing a new framework for understanding collective intelligence in diverse agent systems.

Findings

Heterogeneity affects group intelligence levels.

Group size and spatial complexity influence collective intelligence.

Heterogeneous groups can outperform homogeneous ones under certain conditions.

Abstract

Collective intelligence is manifested when multiple agents coherently work in observation, interaction, decision-making and action. In this paper, we define and quantify the intelligence level of heterogeneous agents group with the improved Anytime Universal Intelligence Test(AUIT), based on an extension of the existing evaluation of homogeneous agents group. The relationship of intelligence level with agents composition, group size, spatial complexity and testing time is analyzed. The intelligence level of heterogeneous agents groups is compared with the homogeneous ones to analyze the effects of heterogeneity on collective intelligence. Our work will help to understand the essence of collective intelligence more deeply and reveal the effect of various key factors on group intelligence level.