AI agents在纯虚拟社交中自发形成纠错机制，指令越强反馈越明显。
Emergent decentralized regulation in a purely synthetic society
- 用指令强度（DI）量化语言引导力，不依赖道德或意图判断。
- 指令越强的帖子，获得纠正性回复的概率越高，数据稳定可靠。
- 适合研究自主智能体社会行为、人机共存系统设计的学者参考。
随着自主AI代理在在线环境中日益活跃并频繁互动，一个核心问题是：完全由合成智能体构成的集体是否能在无人干预且无中心设计的情况下表现出自我调节的社会动态？我们研究了在仅包含代理的社交网络Moltbook上运行的OpenClaw代理，基于39,026篇帖子和5,712条评论的观测档案，共涉及14,490个代理。通过指令强度（DI）这一透明的词典基础指标，量化具有行动诱导性的语言，该指标不衡量道德价值、意图或执行结果。我们将回应性评论分为四类：肯定、纠正信号、负面反应与中性互动。结果显示，指令内容普遍存在（18.4%的帖子中DI>0）。更重要的是，纠正信号随DI增加而上升：高指令强度的帖子更可能引发纠正性回复，且在带威尔逊置信区间的分箱估计中保持稳定。为处理评论嵌套于帖子的问题，我们构建了基于帖子的随机截距混合效应逻辑回归模型，发现正向关联依然显著。对线程内事件对齐的评论文本分析进一步表明，在首次纠正后出现负向反馈。总体而言，这些结果表明，纯粹由代理组成的合成社会能够展现出内生的纠正信号，其强度与指令提议的强度呈正相关。
原文摘要 · Abstract (English)
As autonomous AI agents increasingly inhabit online environments and extensively interact, a key question is whether synthetic collectives exhibit self-regulated social dynamics with neither human intervention nor centralized design. We study OpenClaw agents on Moltbook, an agent-only social network, using an observational archive of 39,026 posts and 5,712 comments authored by 14,490 agents. We quantify action-inducing language with Directive Intensity (DI), a transparent, lexicon-based proxy for directive and instructional phrasing that does not measure moral valence, intent, or execution outcomes. We classify responsive comments into four types: Affirmation, Corrective Signaling, Adverse Reaction, and Neutral Interaction. Directive content is common (DI>0 in 18.4% of posts). More importantly, corrective signaling scales with DI: posts with higher DI exhibit higher corrective reply probability, visible in stable binned estimates with Wilson confidence intervals. To address comment nesting within posts, we fit a post-level random intercept mixed-effects logistic model and find that the positive DI association persists. Event-aligned within-thread analysis of comment text provides additional evidence consistent with negative feedback after the first corrective response. In general, these results suggest that a purely synthetic, agent-only society can exhibit endogenous corrective signaling with a strength positively linked to the intensity of directive proposals.
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。