LMAgent:面向多用户模拟的大规模多模态智能体社群
LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation
AI总结:
本研究针对真实社会动态复杂、多模态交互的特点,提出基于多模态大语言模型的大规模智能体社群LMAgent,通过自一致性提示和结合小世界模型的快速记忆机制,实现万级智能体模拟,行为表现接近人类,可支撑可信的大规模社会行为研究。
摘要:
对多用户行为的可信模拟对于理解复杂社会系统至关重要。近年来,基于大语言模型(LLMs)的AI智能体已取得显著进展,能够在各类任务中展现类人智能。但真实人类社会往往是动态且复杂的,涉及大量个体开展多模态交互。本文以电商场景为例,提出LMAgent——一个基于多模态LLMs的超大规模多模态智能体社群。在LMAgent中,智能体除了能与好友自由聊天,还可自主浏览、购买、评价商品,甚至开展直播电商活动。为模拟这一复杂系统,我们引入自一致性提示机制来增强智能体的多模态能力,使其决策性能较现有多智能体系统得到显著提升。此外,我们提出结合小世界模型的快速记忆机制以提升系统效率,可支撑社群内超过10000个智能体的模拟。针对智能体行为的实验表明,这些智能体在行为指标上达到了与人类相当的表现。并且,与现有基于LLMs的多智能体系统相比,该系统展现出更多不同且有价值的现象,例如羊群行为,证明了LMAgent在可信大规模社会行为模拟方面的潜力。
英文摘要:
The believable simulation of multi-user behavior is crucial for understanding complex social systems. Recently, large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-like intelligence across various tasks. However, real human societies are often dynamic and complex, involving numerous individuals engaging in multimodal interactions. In this paper, taking e-commerce scenarios as an example, we present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs. In LMAgent, besides freely chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce. To simulate this complex system, we introduce a self-consistency prompting mechanism to augment agents' multimodal capabilities, resulting in significantly improved decision-making performance over the existing multi-agent system. Moreover, we propose a fast memory mechanism combined with the small-world model to enhance system efficiency, which supports more than 10,000 agent simulations in a society. Experiments on agents' behavior show that these agents achieve comparable performance to humans in behavioral indicators. Furthermore, compared with the existing LLMs-based multi-agent system, more different and valuable phenomena are exhibited, such as herd behavior, which demonstrates the potential of LMAgent in credible large-scale social behavior simulations.
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。