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

TL;DR

Lyfe Agents are low-cost, real-time generative agents that simulate social behaviors in virtual environments using innovative decision-making and memory mechanisms, enabling human-like interactions at significantly reduced computational expense.

Contribution

The paper introduces Lyfe Agents, combining novel frameworks and memory techniques to achieve efficient, autonomous, and goal-oriented social agents in virtual worlds.

Findings

Agents exhibit human-like social reasoning and collaboration.

Operational costs are 10-100 times lower than existing methods.

Successfully solve complex social tasks like murder mysteries.

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.