Economic World Models
Building AI-system blueprints for agentic economies, policy sandboxes, and self-correcting economic twins.
Economic decisions are usually made in the real world first and evaluated afterward. Economic World Models invert that workflow: they ask how we can build computable economies where heterogeneous agents observe, reason, act, interact, adapt, and co-evolve with markets and institutions before policies, strategies, or AI agents are deployed at scale.
The project develops an implementation-oriented systems blueprint for EconWM systems. It connects economic discipline with AI-system design, treating an economy as a generative engine whose state transitions are produced from inside the modeled world. Agents form beliefs, choose actions, alter the aggregate state, and then respond to the world they helped create.
What The Project Builds
Simulation environments where households, firms, banks, investors, regulators, and AI agents can interact under explicit objectives, constraints, information, and rules.
A taxonomy from fixed rule-based agent worlds to adaptive agents, LLM-based autonomous agents, self-evolving agents, evolving institutions, and sim-to-real economic twins.
Mechanisms for comparing simulated outcomes with real economic evidence, diagnosing deviations, and correcting agents, mechanisms, and transition dynamics over time.
Systems Blueprint
The proposed EconWM architecture has four connected layers: economic agents, economic environments, agent-environment co-evolution, and real-world alignment. This makes the project more than a survey of AI agents in economics: it is a build plan for economic digital twins that can reason, simulate, learn, and stay empirically grounded.
Research Team
The work brings together researchers across Shenzhen Loop Area Institute, CUHK-Shenzhen School of Data Science, the University of Hong Kong, and Nanyang Technological University.
Featured Work
A systems blueprint for implementing Economic World Models as generative AI environments for agent training, planning, policy simulation, and safety analysis.
A curated paper list and resource hub mapping the emerging EconWM literature across agent capability, institutional evolution, and sim-to-real alignment.
The project builds on the Economic World Models and Data-Driven Generative Equilibria agenda, translating the economic framework into an AI-systems roadmap.
From Papers to Systems
The Economic World Models page is the umbrella. Under it, TwinMarket provides a concrete financial market sandbox, MicroVerse explores scientific micro-world simulation, and the curated Awesome Econ World Models repository keeps the paper trail organized. Together they turn the idea of "agents in an environment" into a program about evolving worlds: social worlds, market worlds, biological worlds, and eventually policy-facing digital twins.
Financial agent society where LLM investors create market-level behavior from individual beliefs, desires, intentions, and information flow.
MicroVerseScientific micro-world simulation for biological processes where hidden mechanisms and state transitions matter as much as visual appearance.
Awesome Econ World ModelsLiving bibliography and implementation map for economic agents, agentic economies, institutional evolution, and sim-to-real alignment.