发表机构
Microsoft; University of Illinois Urbana-Champaign; Princeton University; Northeastern University; UCLA（微软; 伊利诺伊大学厄巴纳-香槟分校; 普林斯顿大学; 东北大学; 加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MiniCorp 是一个办公室模拟器，通过模拟公司与市场的双向交互生成纵向及反事实企业数据，用于研究智能体集体运营公司，并验证其能协调决策、适应反馈并维持长期探索。
AI 中文摘要
通往企业级 AGI 的最后一公里是一家能够自我运营的公司。训练和调整此类智能体需要纵向的企业数据，而这些数据仍然稀缺、获取成本高昂，且常常受到隐私限制的约束。历史档案也往往不完整，并且只记录了实际发生的事情，无法展示替代决策的结果。我们引入了 MiniCorp，一个用于研究智能体如何集体运营一家公司并大规模生成企业数据的办公室模拟器。以一家电子商务公司作为演示，MiniCorp 连接了两个相互交互的世界。外部世界模拟了客户、动态竞争对手和市场机制。内部世界由观察事件、讨论选项并做出战略决策的智能体组成。这些决策对市场产生持久影响，由此产生的反馈又为公司的后续决策提供信息。随着公司与市场的互动，MiniCorp 持续记录智能体的沟通和决策。这些记录保留了当时可用的信息和随之而来的业务结果。检查点机制允许在同一情境下重放不同的决策，提供了静态档案中无法获得的比较。我们对照真实市场实证研究中报告的模式评估端到端的保真度。这些评估为智能体提供真实的市场反馈，并降低它们学习利用模拟器缺陷的风险。我们的实验表明，智能体能够跨角色协调，并根据市场反馈调整其决策。在明确的长远战略指导下，它们即使在初期回报不佳的情况下也能维持广告探索。因此，MiniCorp 为研究 AI 运营的公司提供了一个环境，并为智能体训练和评估提供了可扩展的纵向及反事实企业数据来源。
英文摘要
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.
