From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models

2026-08-06

AI Summary

This study addresses the limited endogenous evolutionary capacity of existing economic simulations, which struggle to capture the dynamic co-evolution of heterogeneous agents, markets, and institutions. To bridge this gap, we propose the first systematic Economic World Model (EWM) framework that integrates self-evolving agents, endogenous institutional change, and empirical alignment mechanisms. We further introduce a six-level capability ladder to guide the development trajectory of simulations—from rule-based systems toward high-fidelity, co-evolutionary environments. By synthesizing multi-agent systems, large language models, mechanism design, simulation-to-reality alignment, and continual learning, our approach yields a scalable generative economic engine. A comprehensive literature review reveals that current research remains largely confined to low-level simulations; thus, we provide a complete resource inventory and implementation blueprint to accelerate the development of advanced EWMs, thereby supporting safe training and evaluation of both human decision-making and AI agents.

Abstract

Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their beliefs and actions, and the market and institutional mechanisms through which their interactions produce aggregate outcomes. This paper develops an implementation roadmap for building economic world models as generative engines in which heterogeneous agents act, interact, adapt, and co-evolve with markets and institutions, thereby producing economic dynamics from the inside. We organize EWM systems into a six-level capability ladder, from fixed rule-based agent worlds to adaptive and LLM-based agent worlds, self-evolving agents, evolving institutional worlds, and sim-to-real economic twins aligned with real observations. A systematic literature survey across these levels reveals that existing work remains concentrated in lower-level agent and simulation environments, while systems with self-evolving agents, endogenous institutions, persistent empirical alignment, and validated economic mechanisms remain rare. By translating the EWM agenda into an implementation blueprint, this paper aims to accelerate the development of the next generation of economic simulation environments that can serve as high-fidelity sandboxes for human decision-makers and as training, planning, evaluation, and safety substrates for AI agents. We release a curated paper list and related resources to support future research.

Problem

• Economic World Models
• heterogeneous agents
• endogenous institutions
• sim-to-real alignment
• economic simulation

Innovation

• Economic World Models
• agentic economies
• self-evolving agents
• endogenous institutions
• sim-to-real alignment