arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.02172cs.HCcs.AIcs.LG
收藏

Lyfe Agents:面向低成本实时社交交互的生成式智能体

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

Massachusetts Institute of Technology(麻省理工学院);Peking University(北京大学);LyfeAL

Zhao Kaiya, Michelangelo Naim, Jovana Kondic, Manuel Cortes, Jiaxin Ge, Shuying Luo, Guangyu Robert Yang, Andrew Ahn

AI总结:

针对生成式智能体实时交互成本高的问题,提出Lyfe Agents,通过选项-行动框架等三项创新,在多智能体场景中实现类人社交推理,且计算成本较现有方案低10-100倍。

摘要:

由大语言模型驱动的高自主性生成式智能体有望在虚拟社会中模拟复杂的社会行为。然而,以低计算成本实现与人类的实时交互仍是一大挑战。本文提出了Lyfe Agents,该智能体兼具低成本与实时响应性,同时保持智能性与目标导向性。其核心创新包括:(1)选项-行动框架,降低高层决策成本;(2)异步自我监控机制,提升自我一致性;(3)“总结即遗忘”记忆机制,以低成本优先处理关键记忆项。我们在自研的LyfeGame 3D虚拟环境平台的多个多智能体场景中,评估了Lyfe Agents的自我动机与社交能力。当搭载这些类脑技术时,Lyfe Agents能展现出类人的自驱型社交推理能力,例如智能体可通过自主协作与信息交换侦破案件(谋杀谜案)。同时,这些技术使Lyfe Agents的运行计算成本比现有方案低10-100倍。研究结果凸显了自主生成式智能体在丰富人类虚拟世界社交体验方面的变革性潜力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑