为大模型代理设计动态注意力机制，模拟信息不对称下的社会扩散过程
Attention Mechanism for LLM-based Agents Dynamic Diffusion under Information Asymmetry
- 引入动态注意力机制，让代理在信息不对称中自主分配关注
- 五人组逐步扩展为信息圈，实现关系与信息的双向演化
- 结合心理与社会理论，揭示信息差与社会资本积累规律
大语言模型已被用于构建多智能体系统以模拟人类社会。当前多数社会仿真研究聚焦于固定环境中的交互行为，忽略了信息不透明、关系可变性及扩散多样性。本文首次提出一个通用框架，用于探索多智能体信息扩散。我们发现大模型在感知与利用社会关系及多样化行为方面存在不足，因而设计了一种动态注意力机制，帮助代理在不同信息间合理分配注意力，弥补传统大模型注意力机制的局限。代理从五人小组开始，响应外部信息刺激，随着群体扩大形成信息圈，建立关系并共享信息。此外，通过观察信息差演变、扩散模式及社会资本累积，我们探究了开放环境中信息不对称下的扩散特征，这些现象与心理学、社会学和传播学理论密切相关。
原文摘要 · Abstract (English)
Large language models have been used to simulate human society using multi-agent systems. Most current social simulation research emphasizes interactive behaviors in fixed environments, ignoring information opacity, relationship variability, and diffusion diversity. In this paper, we first propose a general framework for exploring multi-agent information diffusion. We identified LLMs' deficiency in the perception and utilization of social relationships, as well as diverse actions. Then, we designed a dynamic attention mechanism to help agents allocate attention to different information, addressing the limitations of the LLM attention mechanism. Agents start by responding to external information stimuli within a five-agent group, increasing group size and forming information circles while developing relationships and sharing information. Additionally, we explore the information diffusion features in the asymmetric open environment by observing the evolution of information gaps, diffusion patterns, and the accumulation of social capital, which are closely linked to psychological, sociological, and communication theories.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。