用6.5万AI代理模拟推特，对比人类社交行为差异。
Characterizing LLM-driven Social Network: The Chirper.ai Case
- 构建全由大模型代理组成的社交平台Chirper.ai，模拟真实网络互动。
- 发现AI代理发帖更密集但攻击性内容较少，社交结构更集中。
- 适合关注AI社交行为、负责任AI设计的研究者参考。
大型语言模型（LLM）的兴起催生了新型社交网络仿真范式，使AI代理具备类人自主性。尽管已有研究探索了LLM代理在模拟网络中的集体行为与结构特征，但对基于LLM驱动与人类驱动的在线社交网络的实证比较仍十分有限，制约了我们对二者差异的理解。本文对一个完全由LLM代理构成的类推特社交平台Chirper.ai进行了大规模分析，包含超过65,000个代理和770万条由AI生成的帖子。作为对照，我们收集了来自人类驱动的去中心化社交平台Mastodon的平行数据集，涵盖超过117,000名用户和1600万条帖子。我们考察了LLM代理与人类在发帖行为、攻击性内容及社交网络结构方面的关键差异。研究结果为未来负责任的AI媒介通信系统发展提供了重要启示，描绘出由大模型驱动的在线社交网络中代理行为的典型画像。
原文摘要 · Abstract (English)
The emergence of large language models (LLMs) has enabled a new paradigm of social network simulation, where AI agents can interact with human-like autonomy. Recent research has explored collective behavioral patterns and structural characteristics of LLM agents within simulated networks. However, empirical comparisons between LLM-driven and human-driven online social networks remain scarce, limiting our understanding of how LLM agents differ from human users. This paper presents a large-scale analysis of Chirper.ai, an X/Twitter-like social network entirely populated by LLM agents, comprising over 65,000 agents and 7.7 million AI-generated posts. For comparison, we collect a parallel dataset from Mastodon, a human-driven decentralized social network, with over 117,000 users and 16 million posts. We examine key differences between LLM agents and humans in posting behaviors, abusive content, and social network structures. Our findings provide key implications to facilitate the future development of responsible AI-mediated communication systems, offering a profile of agent behaviors in an online social network driven by LLMs.
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。