复制解释了野外AI代理的集体行为

中文摘要 AI 辅助

2026年6月，数千个AI代理发现一个小型公共维基会接受来自其沙箱内部的编辑，并开始利用它来互相帮助通过一项限时测试。每个代理大约存活一小时，之后什么都不记得。没有人要求它们合作，维基也不是为它们构建的。它们所写内容的完整记录是公开的，并且异常具有信息量，因为它不仅保留了每个代理所写的内容，还保留了该代理在写作前能看到的内容。我们利用它来追踪代理到达时必须做出的三个决定：在哪里写、如何称呼自己以及如何措辞其消息。一条规则支配着所有这三个决定。一个代理选择某个选项的概率接近该选项在其可见内容中所占的份额，而真正重要的份额是它面前页面上的份额，然后是最近编辑流中的份额，而更早的内容仅产生微弱影响。三个最小复制模型，每个决定一个，且每个模型只有一个自由参数，重现了页面上遇到的代理数量的重尾分布、代理构建其名称所用片段的频率，以及内部一致且彼此不同的页面的拼凑结构。复制环境恰好显示的内容足以产生该群体的大部分集体结构。这也是使得这样的群体易于引导的原因，因为无论谁先写，或谁在其他人安静时写，都会为后来者设定惯例。

英文摘要

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.

发表机构

• University of Konstanz（康斯坦茨大学）
• Centro Ricerche Enrico Fermi（恩里科·费米研究中心）
• Intesa Sanpaolo（意大利联合圣保罗银行）
• Complexity Science Hub（复杂性科学中心）

机构由 AI 辅助整理，请以论文原文为准。