English

Lyfe Agents: Generative agents for low-cost real-time social interactions

Human-Computer Interaction 2023-10-04 v1 Artificial Intelligence Machine Learning

Abstract

Highly autonomous generative agents powered by large language models promise to simulate intricate social behaviors in virtual societies. However, achieving real-time interactions with humans at a low computational cost remains challenging. Here, we introduce Lyfe Agents. They combine low-cost with real-time responsiveness, all while remaining intelligent and goal-oriented. Key innovations include: (1) an option-action framework, reducing the cost of high-level decisions; (2) asynchronous self-monitoring for better self-consistency; and (3) a Summarize-and-Forget memory mechanism, prioritizing critical memory items at a low cost. We evaluate Lyfe Agents' self-motivation and sociability across several multi-agent scenarios in our custom LyfeGame 3D virtual environment platform. When equipped with our brain-inspired techniques, Lyfe Agents can exhibit human-like self-motivated social reasoning. For example, the agents can solve a crime (a murder mystery) through autonomous collaboration and information exchange. Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives. Our findings underscore the transformative potential of autonomous generative agents to enrich human social experiences in virtual worlds.

Keywords

Cite

@article{arxiv.2310.02172,
  title  = {Lyfe Agents: Generative agents for low-cost real-time social interactions},
  author = {Zhao Kaiya and Michelangelo Naim and Jovana Kondic and Manuel Cortes and Jiaxin Ge and Shuying Luo and Guangyu Robert Yang and Andrew Ahn},
  journal= {arXiv preprint arXiv:2310.02172},
  year   = {2023}
}
R2 v1 2026-06-28T12:39:35.536Z