用虚拟艺术家模拟创造力系统，发现协作更易产生创意成果。
Creative Agents: Simulating the Systems Model of Creativity with Generative Agents
- 用大模型构建虚拟艺术家，分孤立与协作两种场景模拟
- 协作环境下生成作品的创意性显著更高（用户与LLM评估）
- 适合对人机共创、艺术生成感兴趣的读者
随着生成式AI在图像、视频和音乐领域的普及，模型质量与性能快速提升。然而，对人工智能是否具备‘创造力’的关注仍不足。本研究基于Csikszentmihalyi提出的创造力系统模型，利用大语言模型（LLMs）和文本提示构建虚拟艺术家，模拟两种情境：1）孤立的艺术家；2）多智能体协作系统。通过用户研究与大模型评估，对比生成作品的多样性与整体创意水平。结果表明，在创造力系统模型框架下，生成代理的表现更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。