Creative Agents: Simulating the Systems Model of Creativity with Generative Agents

TL;DR

This paper explores simulating the systems model of creativity using virtual agents powered by large language models, comparing isolated and multi-agent setups to evaluate their creative output.

Contribution

It introduces a novel simulation of the systems model of creativity with generative agents and compares their performance in different social configurations.

Findings

Multi-agent systems show higher creativity in generated artifacts.

User studies and LLM analysis indicate improved creativity in multi-agent setups.

Simulation supports the potential of AI agents to exhibit creative behaviors.

Abstract

With the growing popularity of generative AI for images, video, and music, we witnessed models rapidly improve in quality and performance. However, not much attention is paid towards enabling AI's ability to "be creative". In this study, we implemented and simulated the systems model of creativity (proposed by Csikszentmihalyi) using virtual agents utilizing large language models (LLMs) and text prompts. For comparison, the simulations were conducted with the "virtual artists" being: 1)isolated and 2)placed in a multi-agent system. Both scenarios were compared by analyzing the variations and overall "creativity" in the generated artifacts (measured via a user study and LLM). Our results suggest that the generative agents may perform better in the framework of the systems model of creativity.