AI 公司自己经营自己，先得有个能重来的办公室
训练一个能自己经营公司的 AI，缺的不是算法，是数据：真实企业数据又贵又涉及隐私，而且历史档案只记录「实际发生了什么」，永远看不到「如果当时选了另一条路会怎样」。这篇论文造了个叫 MiniCorp 的办公室模拟器，里面有一群 AI 员工，外面有模拟的顾客和竞争对手，AI 们开会、讨论、做决策，决策反过来影响市场，市场再反馈给公司。关键设计是「存档点」:同一个局面可以回放，换一种决策重来，于是能对比不同选择的结果——这是真实档案永远给不了的。实验里，AI 员工能跨角色协作、根据市场反馈调整策略，在明确长期目标下，即使短期广告效果差也能坚持投入。它不是你明天能用上的东西，但它是通往「AI 自己管公司」这条路上，一块必要的垫脚石。
📄 原文摘要(英文)
The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly to acquire, and often restricted by privacy constraints. Historical archives are also frequently incomplete and record only what actually happened. They cannot show the outcomes of alternative decisions. We introduce MiniCorp, an office simulator for studying how agents can collectively run a company while generating enterprise data at scale. Using an e-commerce company as a demonstration, MiniCorp connects two interacting worlds. The external world models customers, dynamic competitors, and market mechanisms. The internal world consists of agents that observe events, discuss their options, and make strategic decisions. These decisions have lasting effects on the market, and the resulting feedback informs the firm's later decisions. As the firm and market interact, MiniCorp continuously records the agents' communications and decisions. These records preserve the information available at the time and the business results that followed. Checkpointing allows the same situation to be replayed under different decisions, providing comparisons unavailable in static archives. We evaluate end-to-end fidelity against patterns reported in empirical studies of real markets. These evaluations provide agents with realistic market feedback and reduce the risk that they learn to exploit flaws in the simulator. Our experiments show agents coordinating across roles and adapting their decisions to market feedback. With explicit long-term strategic guidance, they also sustain advertising exploration despite weak early returns. MiniCorp thus provides an environment for studying AI-run companies and a scalable source of longitudinal and counterfactual enterprise data for agent training and evaluation.