Evaluation Mechanism of Collective Intelligence for Heterogeneous Agents Group
This work helps researchers understand the essence of collective intelligence and the impact of key factors on group intelligence level, but it appears incremental as it builds on existing evaluation methods for homogeneous agents.
The paper tackled the problem of quantifying collective intelligence in heterogeneous agent groups by extending the Anytime Universal Intelligence Test (AUIT) from homogeneous groups, analyzing how intelligence level relates to factors like agent composition, group size, spatial complexity, and testing time, and comparing heterogeneous with homogeneous groups to assess heterogeneity's effects.
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.