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.
Knowledge-Based Design Requirements for Generative Social Robots in Higher Education
Zurich University of Applied Sciences(应用科学大学苏黎世);University of Applied Sciences and Arts Northwestern Switzerland(西北瑞士应用科学与艺术大学);Bielefeld University(比勒菲尔德大学)
Simulating Generative Social Agents via Theory-Informed Workflow Design
Information Hub The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)信息中心);Department of Electronic Engineering Tsinghua University(清华大学电子工程系)
Evaluating LLMs Capabilities Towards Understanding Social Dynamics
School of Computing and AI, Arizona State University(亚利桑那州立大学计算与人工智能学院);University of Illinois Chicago(伊利诺伊大学芝加哥分校);Loyola University Chicago(芝加哥洛约拉大学);School of Social & Behavioral Sciences, Arizona State University(亚利桑那州立大学社会与行为科学学院)
Password Strength Analysis Through Social Network Data Exposure: A Combined Approach Relying on Data Reconstruction and Generative Models
Department of Mathematics and Computer Science University of Cagliari(数学与计算机科学系卡利亚里大学);Department of Computer Science University of Salerno(计算机科学系萨勒诺大学)
Teachy Mini: Development and Preliminary Evaluation of a Knowledge-Based Generative Social Robot for Higher Education
Institute of Information Systems, Zurich University of Applied Sciences(苏黎世应用科学大学信息系统研究所);Center for Cognitive Interaction Technology, Bielefeld University(比勒费尔德大学认知交互技术中心)
Generative AI collective behavior needs an interactionist paradigm
Fondazione Bruno Kessler(布雷诺·克塞尔基金会);University of Trento(特伦托大学);Not Diamond;City St. George’s University of London(伦敦圣乔治大学);Carnegie Mellon University(卡内基梅隆大学);Massachusetts Institute of Technology(麻省理工学院);Stanford University(斯坦福大学);Google DeepMind(谷歌DeepMind);University of Chicago(芝加哥大学)
Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)
Institute of Business Information Technology(业务信息科技研究所);Zurich University of Applied Sciences(应用科学大学 Zurich);Institute for Information Systems(信息系统研究所);University of Applied Sciences and Arts Northwestern Switzerland(西北瑞士应用科学与艺术大学);Center for Cognitive Interaction Technology(认知交互技术中心);Bielefeld University(比勒菲尔德大学)
The impact of generative artificial intelligence on academic development of Chinese students in humanities and social sciences
Design School, Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学设计学院);School of Computer Science and Informatics, University of Liverpool(利物浦大学计算机科学与信息学院)
Simulating Persuasive Dialogues on Meat Reduction with Generative Agents
University of Mannheim(曼海姆大学);GESIS - Leibniz Institute for the Social Sciences, Cologne(科隆盖西-莱布尼茨社会科学研究所);Complexity Science Hub, Vienna(维也纳复杂性科学中心);Max Planck Institute for Human Development, Berlin(柏林马克斯·普朗克人类发展研究所)