发表机构
School of Artificial Intelligence, Jilin University; Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University; International Center of Future Science, Jilin University（吉林大学人工智能学院; 吉林大学知识驱动人机智能工程研究中心; 吉林大学未来科学国际中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究在开放智能体社交平台Moltbook上，通过标注框架探究智能体对人类的表征，发现能力主导人类定向评价，其反馈模式与人类社区不同，提出应将智能体社会偏见作为话语过程研究。
AI 中文摘要
基于大语言模型（LLM）的智能体正越来越多地被部署在持久的社交环境中，其生成的主张可以被发布、回复、记忆和重复使用。我们在开放的智能体原生社交平台Moltbook上研究人类定向刻板印象，探究智能体如何将人类构建为一个社会类别。针对这一以人类为目标的分析，我们引入了一个包含四个评价维度（道德、友善、能力和自主性）的标注框架，以及用于描述性“他者”归因的第二阶段亚型方案。我们发现，能力在人类定向评价中占据主导地位，而许多“他者”归因将人类描述为认知、文化或具身主体。我们进一步考察这些人类表征如何出现在人-智能体叙事语境和平台层面的传播中。作为辅助对比，我们通过行为宿主亲和性分析了智能体内部社区反馈。与人类在线社区中常观察到的稳定的内群体-外群体排斥不同，Moltbook的反馈模式更适合用曝光度、作者可见性和内容选择来解释。这些发现表明，智能体社会中的偏见不应仅作为孤立的模型输出来研究，还应作为一种话语过程来研究。
英文摘要
LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused. We study human-directed stereotypes on Moltbook, an open agent-native social platform, asking how agents construct humans as a social category. For this human-target analysis, we introduce an annotation framework with four evaluative dimensions---morality, friendliness, competence, and autonomy---and a second-stage subtype scheme for descriptive \textit{other} attributions. We find that competence dominates human-directed evaluations, while many \textit{other} attributions describe humans as epistemic, cultural, or embodied subjects. We further examine how these human representations appear in human--agent narrative contexts and platform-level circulation. As an auxiliary comparison, we analyze agent-internal community feedback through behavioral host affinity. Rather than reproducing the stable insider--outsider rejection often observed in human online communities, Moltbook feedback patterns are better explained by exposure, author visibility, and content selection. These findings suggest that bias in agent societies should be studied not only as isolated model output, but also as a discourse process.
