发表机构
Shenzhen Loop Area Institute; School of Data Science, The Chinese University of Hong Kong, Shenzhen; University of Hong Kong; Nanyang Technological University（深圳河套学院; 香港中文大学（深圳）数据科学学院; 香港大学; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出经济世界模型（EWM）的六级能力阶梯实施蓝图，旨在加速可作为人类决策沙箱与AI智能体基础的下一代高保真经济模拟环境开发。
AI 中文摘要
经济世界模型（Economic World Models，EWMs）是生成式经济模型，通过对异质智能体、其信念与行为，以及它们的互动产生总量结果的市场和制度机制进行建模，从内部模拟经济的演化。本文制定了构建EWMs的实施路线图，将其作为生成式引擎，其中异质智能体与市场和制度共同行动、互动、适应和协同演化，进而从内部产生经济动态。我们将EWM系统组织为六级能力阶梯，从基于固定规则的智能体世界，到自适应和基于大语言模型（LLM）的智能体世界、自演化智能体、演化制度世界，以及与真实观测对齐的虚实结合经济孪生体。对这些层级的系统文献调查显示，现有研究仍集中在较低层级的智能体和模拟环境，而具备自演化智能体、内生制度、持续经验对齐和经验证经济机制的系统仍较为罕见。本文通过将EWM议程转化为实施蓝图，旨在加速下一代经济模拟环境的开发，这些环境可作为人类决策者的高保真沙箱，以及AI智能体的训练、规划、评估和安全基础。我们发布了精选论文列表和相关资源以支持未来研究。
英文摘要
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.
CommentsProject page: https://github.com/FreedomIntelligence/Awesome-Economic-World-Models
