MiniCorp：AI 智能體公司的最後一哩路
MiniCorp: The Last Mile of the AI Agent Firm
MiniCorp 是一個辦公室模擬器，讓 AI 智能體協作營運公司，並大規模生成供智能體訓練與評估使用的企業數據。它記錄智能體的通訊、決策及後續業務結果，並可重播相同情境以比較不同決策。實驗顯示，智能體能跨角色協作，並根據市場回饋調整決策。
Published on Oct 5
·
on Oct 7
Authors:
,
,
,
,
,
,
,
Abstract
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.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2610.05912
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.05912 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.05912 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.05912 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源：HuggingFace Daily Papers（社區熱門論文） · huggingface.co