The authors designed MiniCorp as an office simulator with two interacting worlds.
MiniCorp: a simulator for studying AI-run companies and generating enterprise data
The authors introduce a checkpointable office simulator where LLM-based agents collectively operate a firm in an evolving market, generating longitudinal and counterfactual data for training and evaluation.
Big Tech
Jingying Zeng · Zhenwei Dai · Jinning Li · Changho Shin · Dylan Zhang · Yuxuan Lu · +3 more
Microsoft · University of Illinois Urbana-Champaign · Princeton University · Northeastern University · UCLA
Research Digest··3 min read
The authors present MiniCorp, a simulator that couples an internal world of persistent agent roles with an external world of customers, competitors, and market mechanisms.
Why this paper
From Microsoft and 4 others
In one line
MiniCorp simulates persistent AI-run firms and evolving markets, generating longitudinal, counterfactual enterprise data for training and evaluating long-horizon organizational agents.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§