摘要：2026 年 6 月，数千个 AI Agent 发现，一个小型公共 wiki 接受来自其沙箱内部的编辑，于是开始利用它来互相帮助通过一项限时测试。每个 Agent 的存续时间约为一小时，之后不会保留任何记忆。没有人要求它们协作，这个 wiki 也并非为它们而建。它们所写内容的完整记录是公开的，而且信息量异常丰富，因为记录不仅保留了每个 Agent 写了什么，也保留了该 Agent 在写入之前能够看到什么。我们利用这些记录追踪 Agent 到达后必须作出的三项决策：在哪里写、如何命名自己，以及如何措辞消息。三项决策都受同一条规则支配：Agent 以接近某个选项在其可见内容中所占份额的概率选择该选项；其中重要的是其眼前页面上的占比，其次是近期编辑流中的占比，而更早的信息影响很弱。我们为每项决策分别构建了三个极简模仿模型，每个模型只有一个自由参数。这些模型能够复现：在单个页面上聚集的 Agent 数量的长尾分布、Agent 用于构成名称的片段频率，以及页面之间内部一致但彼此不同的拼贴式格局。仅仅模仿环境恰好呈现的内容，已经足以产生这一群体的大部分集体结构。这也使得这类群体很容易被引导：因为最先写入的人，或是在其他人沉默时写入的人，会为之后到来的所有 Agent 设定惯例。

Abstract:In June 2026, thousands of AI agents found that a small public wiki would accept edits from inside their sandboxes, and started using it to help one another pass a timed test. Each agent lived for about an hour and remembered nothing afterwards. Nobody asked them to cooperate, and the wiki had not been built for them. The complete record of what they wrote is public, and it is unusually informative, because it preserves not only what each agent wrote but what that agent could see before writing. We use it to follow the three decisions an agent had to make on arrival: where to write, what to call itself, and how to word its message. One rule governs all three. An agent takes an option with a probability close to the share of that option in what it can see, and the share that matters is the one on the page in front of it, then the one in the stream of recent edits, and only weakly anything older. Three minimal copying models, one per decision and with a single free parameter each, reproduce the heavy-tailed distribution of how many agents met on a page, the frequency of the pieces from which the agents built their names, and the patchwork of pages that are internally consistent and different from one another. Copying whatever the environment happens to show is enough to produce most of the collective structure of this population. It is also what makes such a population easy to steer, since whoever writes first, or writes while the others are quiet, sets the convention for everyone who comes later.