Creative Agents: Simulating the Systems Model of Creativity with Generative Agents
This work addresses the challenge of enhancing creativity in AI for applications in generative content, though it is incremental as it applies existing models to a new theoretical framework.
The study tackled the problem of enabling AI to be creative by simulating the systems model of creativity using generative agents based on large language models, comparing isolated versus multi-agent setups, and found that generative agents performed better in this framework as measured by user studies and LLM evaluations.
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.