- [2026/03/24] Initial release of the Awesome-Econ-World-Models GitHub repository.
An Economic World Model (EconWM) is a data-driven imagination engine for understanding and simulating economic systems, enabling humans and machines to explore what-if futures under alternative actions and interventions.
Broad overviews that help newcomers understand the landscape.
-
Understanding World or Predicting Future? A Survey of World Models,
arxiv, 2024.11. [Paper] -
From Efficient Multimodal Models to World Models: A Survey,
arxiv, 2024.07. [Paper] -
A Comprehensive Survey on World Models for Embodied AI,
arxiv, 2025.10. [Paper] -
Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond,
arxiv, 2024.05. [Paper] -
World models for autonomous driving: An initial survey,
IEEE Transactions on Intelligent Vehicles, 2024.05. [Paper] -
Learning to Model the World: A Survey of World Models in Artificial Intelligence,
Preprints.org, 2026.03. [Paper]
Foundational papers that shape the modern notion of learning internal models of environment dynamics.
-
World Models,
arxiv, 2018.03. [Paper] -
Recurrent World Models Facilitate Policy Evolution,
NeurIPS, 2018.12. [Paper] -
Dream to Control: Learning Behaviors by Latent Imagination,
arxiv, 2019.12. [Paper] -
Mastering Atari with Discrete World Models (DreamerV2),
arxiv, 2020.10. [Paper] -
A Generalist Agent,
arxiv, 2022.05. [Paper] -
A Path Towards Autonomous Machine Intelligence (JEPA),
OpenReview, 2022.06. [Paper] -
Inner Monologue: Embodied Reasoning through Planning with Language Models,
arxiv, 2022.07. [Paper] -
Mastering Diverse Domains through World Models (DreamerV3),
arxiv, 2023.01. [Paper] -
Language Models Represent Space and Time, arxiv,
2023.10. [Paper] -
Mastering Diverse Control Tasks Through World Models, Nature,
2025.04. [Paper] -
General Agents Need World Models,
ICML, 2025.07. [Paper]
Representative works that extend world models from latent RL environments to multimodal generation, interactive simulation, and embodied environments.
-
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge,
NeurIPS, 2022.12. [Paper] -
Learning to Model the World with Language,
arxiv, 2023.08. [Paper] -
GAIA-1: A Generative World Model for Autonomous Driving,
arxiv, 2023.09. [Paper] -
UniSim - Learning Interactive Real-World Simulators,
arxiv, 2023.10. [Paper] -
Sora - Video Generation Models as World Simulators,
OpenAI Blog, 2024.02. [Paper] -
Genie: Generative Interactive Environments,
OpenReview, 2024.02. [Paper] -
MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control,
arxiv, 2024.03. [Paper] -
SIMA/SIMA 2 - Scalable Instructable Multiworld Agent,
Google DeepMind Blog, 2024.03. [Paper] [Paper] -
Pandora: Towards General World Model with Natural Language Actions and Video States,
arxiv, 2024.06. [Paper] -
Genie 2: A Large-Scale Foundation World Model,
Google DeepMind Blog, 2024.08. [Paper] -
Project Sid: Many-agent simulations toward AI civilization,
arxiv, 2024.11. [Paper] -
Sim-gen: Simulator-conditioned driving scene generation,
NeurIPS, 2024.12. [Paper] -
Embodied AI Agents: Modeling the World,
arxiv, 2025.06. [Paper] -
Embodied AI: From LLMs to World Models,
arxiv, 2025.09. [Paper] -
EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds,
ICCV, 2025.10. [Paper] -
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation,
ICCV, 2025.10. [Paper]
- World Models: Computing the Uncomputable,
2026.03. [link] [WeChat repost] - V-JEPA: The next step toward Yann LeCun’s vision of advanced machine intelligence (AMI),
2024.02. [link] - Yann LeCun on a vision to make AI systems learn and reason like animals and humans,
2022.02. [link] - Yann LeCun: AI Doesn’t Need Our Supervision,
2022.02. [link]
This section traces the evolution of economic modeling from rules and data to agents, multi-agent interaction, and full economic environments.
-
Nash Equilibrium: "Non-Cooperative Games",
Econometrica 1951.09. [Paper] -
General Equilibrium: "Existence of an Equilibrium for a Competitive Economy",
Econometrica 1954.07. [Paper]
-
Neoclassical Synthesis (IS-LM): "Mr. Keynes and the "Classics"; A Suggested Interpretation",
Econometrica 1937.04. [Paper] -
New Classical (RBC): "Time to Build and Aggregate Fluctuations",
Econometrica 1982.11. [Paper]
-
CGE: "Applied General-Equilibrium Models of Taxation and International Trade: An Introduction and Survey",
JEL 1984.09. [Paper] -
DSGE: "Shocks and Frictions in US Business Cycles: A Bayesian DSGE Approach",
AER 2007.06. [Paper]
-
Text-Based Volatility Signal: "News Implied Volatility and Disaster Concerns"
UTD-J. Financ. Econ. 2017.01. [Paper] -
Photo-Based Sentiment Index: "A Picture Is Worth a Thousand Words: Measuring Investor Sentiment by Combining Machine Learning and Photos from News"
UTD-J. Financ. Econ. 2022.04. [Paper] -
Transaction-Based Fraud Detection Features: "Peer-to-Peer Loan Fraud Detection: Constructing Features from Transaction Data"
UTD-MIS 2022.09. [Paper] -
Informed Trading Measure: "Informed Trading Intensity"
UTD-J. Finance 2024.02. [Paper] -
Feature Engineering for ML Signals: "Machine Learning from a Universe of Signals: The Role of Feature Engineering"
UTD-J. Financ. Econ. 2025.10. [Paper]
-
Dynamic Graph Neural Network for Stocks: "Inductive Representation Learning on Dynamic Stock Co-Movement Graphs for Stock Predictions"
UTD-INFORMS J Comput 2022.07. [Paper] -
DL for Pricing: "Deep Learning in Asset Pricing"
UTD-Manage. Sci. 2024.02. [Paper] -
Vocal Tone DL Model: "Listen Closely: Measuring Vocal Tone in Corporate Disclosures"
UTD-J. Account. Res. 2025.09. [Paper]
-
FinBERT: "FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining"
IJCAI 2021.01. [Paper] -
Knowledge-Enhanced Text Embedding: "Analyzing Firm Reports for Volatility Prediction: A Knowledge-Driven Text-Embedding Approach"
UTD-INFORMS J Comput 2022.01. [Paper] -
BloombergGPT: "BloombergGPT: A Large Language Model for Finance"
arXiv 2023.03. [Paper]
-
GPT Game Theory: "GPT in Game Theory Experiments"
arXiv 2023.05. [Paper] -
GPT Economic Rationality: "The Emergence of Economic Rationality of GPT"
arXiv 2023.05. [Paper] -
Strategic Prompt Engineering: "The Crowdless Future? Generative AI and Creative Problem-Solving"
UTD-Organ. Sci. 2024.09. [Paper] -
LASER&BEAM: "Let the Laser Beam Connect the Dots: Forecasting and Narrating Stock Market Volatility"
UTD-INFORMS J Comput 2024.11. [Paper] -
Context-Aware LLM for Market Impact: "Context-Aware Language Models for Forecasting Market Impact from Sequences of Financial News"
arXiv 2025.09. [Paper] -
Persona-based Prompting: "Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas"
ICAIF 2025.11. [Paper] -
LLM as Homo Silicus: "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?"
NBER 2026.02. [Paper]
-
First Modern ABM: "Investment rules, margin, and market volatility"
JPM 1989.04. [Paper] -
ACE1: "Agent-Based Computational Economics: Growing Economies From the Bottom Up"
Artif. Life 2002.01. [Paper] -
ABM Financial Markets Survey: "Agent-Based Models of Financial Markets"
arXiv 2007.01. [Paper] -
ACE2: "Handbook of Computational Economics, Vol. 2: Agent-Based Computational Economics"
INFORMS J. Appl. Anal. 2007.05. [Paper] -
ABM in Econ: "Agent‐Based Modelling in Economics"
Wiley 2015.11. [Paper] -
ABM in Macro-Econ: "Agent-based macroeconomics"
Handb. Comput. Econ. 2018.02. [Paper] -
SABCEMM: "Simulation of Stylized Facts in Agent-Based Computational Economic Market Models"
arXiv 2018.11. [Paper] -
Complexity Economics: "Foundations of Complexity Economics"
Nat. Rev. Phys. 2021.01. [Paper] -
Bounded Rationality ABM: "Modeling the Out-of-Equilibrium Dynamics of Bounded Rationality and Economic Constraints"
arXiv 2021.06. [Paper] -
Flash Crash ABM: "High-Frequency Financial Market Simulation and Flash Crash Scenarios Analysis: An Agent-Based Modelling Approach"
arXiv 2022.08. [Paper] -
ABIDES-Economist: "ABIDES-Economist: Agent-Based Simulator of Economic Systems with Learning Agents"
arXiv 2024.02. [Paper] -
Social Media Bubble ABM: "Simulation of Social Media-Driven Bubble Formation in Financial Markets using an Agent-Based Model with Hierarchical Influence Network"
arXiv 2024.09. [Paper] -
Prediction Market Manipulation: "Manipulation in Prediction Markets: An Agent-Based Modeling Experiment"
arXiv 2025.01. [Paper]
-
EconAgent: "EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities"
arXiv 2023.10. [Paper] -
ASFM: "Simulating Financial Market via Large Language Model based Agents"
arXiv 2024.06. [Paper] -
TradingAgents: "TradingAgents: Multi-Agents LLM Financial Trading Framework"
arXiv 2024.12. [Paper] [Project] -
Framework: "A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis"
arXiv 2025.02. [Paper] -
LLM Trading Agents: "Can Large Language Models Trade? Testing Financial Theories with LLM Agents in Market Simulations"
arXiv 2025.04. [Paper] -
Digital Twin Behavioral Dataset: "Twin-2K-500: A Data Set for Building Digital Twins of over 2,000 People Based on Their Answers to over 500 Questions"
arXiv 2025.05. [Paper] -
TwinMarket: "TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets"
arXiv 2025.10. [Paper] -
Macro Expectation Simulation: "Simulating Macroeconomic Expectations Using LLM Agents"
arXiv 2025.11. [Paper] -
MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment,
arXiv 2026.03. [Paper]
-
Environment + Single Agent: "AlphaManager: A Data-Driven-Robust-Control Approach to Corporate Finance"
SSRN 2025.03. [Paper] -
Game-Theoretic XAI Regulation Model: "Regulating Explainable Artificial Intelligence (XAI) May Harm Consumers"
UTD-Mark. Sci. 2025.05. [Paper] -
Algorithmic Lending Competition Model: "Algorithmic Lending, Competition, and Strategic Provision of Preapproval Tools"
UTD-Mark. Sci. 2025.08. [Paper]
-
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies,
arxiv, 2022.08. [Paper] -
Social simulacra： Creating Populated Prototypes for Social Computing Systems,
UIST, 2022.10. [Paper] -
Voyager: An Open-Ended Embodied Agent with Large Language Models,
arxiv, 2023.05. [Paper] -
S3： Social-network Simulation System with Large Language Model-Empowered Agents,
arxiv, 2023.07. [Paper] -
Out of One, Many: Using Language Models to Simulate Human Samples,
Political Analysis, 2023.09. [Paper] -
AI Town – Generative Agents: Interactive Simulacra of Human Behavior,
UIST, 2023.10. [Paper] -
Waragent - War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars,
arxiv, 2023.11. [Paper] -
Bank Run, Interrupted: Modeling Deposit Withdrawals with Generative AI,
SSRN, 2023.12. [Paper] -
ABIDES-Economist: Agent-Based Simulator of Economic Systems with Learning Agents,
arxiv, 2024.02. [Paper] -
Automated social science: Language Models as Scientist and Subjects,
NBER, 2024.04. [Paper] -
Stockagent - When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments,
arxiv, 2024.07. [Paper] -
Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games,
arxiv, 2024.10. [Paper] -
LLM voting: Human Choices and AI Collective Decision-Making,
AIES, 2024.10. [Paper] -
AgentSociety： Large-Scale Simulation of LLM-Driven Generative Agents to Advance the Understanding of Human Behaviors and Society,
SSRN, 2025.01. [Paper] -
FOMC In Silico: A Multi-Agent System for Monetary Policy Decision Modeling,
SSRN, 2025.01. [Paper] -
Playing Repeated Games With Large Language Models,
Nature Human Behaviour, 2025.02. [Paper] -
MiniFed: LLMs-based Agentic-Workflow for Simulating FOMC Meetings,
PACIS, 2025.07. [Paper] -
Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona?,
arxiv, 2025.08. [Paper] -
InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance,
arxiv, 2025.11. [Paper] -
Evaluating and Aligning Human Economic Risk Preferences in LLMs,
EMNLP, 2025.12. [Paper] -
Consumption and Savings with Large Language Model Agents,
SSRN, 2026.02. [Paper]
-
The AI Economist: Taxation Policy Design via Two-level Deep Multiagent Reinforcement Learning,
Science Advances, 2022.05. [Paper] -
Using LLMs for Market Research,
SSRN, 2023.03. [Paper] -
Simulated Economic Agents - Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?,
NBER, 2023.04. [Paper] -
Are LLMs Rational Investors? A Study on Detecting and Reducing the Financial Bias in LLMs,
arxiv, 2024.02. [Paper] -
EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities,
ACL, 2024.08. [Paper] -
Can LLMs Mimic Human-Like Mental Accounting and Behavioral Biases?,
ACM, 2024.08. [Paper] -
LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory,
arxiv, 2024.08. [Paper] -
Project Sid: Many-agent simulations toward AI civilization,
arxiv, 2024.11. [Paper] -
SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent,
EMNLP Findings, 2024.11. [Paper] -
A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis,
arxiv, 2025.02. [Paper] -
LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra,
arxiv, 2025.07. [Paper] -
Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare,
arxiv, 2025.10. [Paper] -
RISE: Self-Improving Robot Policy with Compositional World Model,
arxiv, 2026.02. [Paper] [Project]
-
PolicySimEval: A Benchmark for Evaluating Policy Outcomes through Agent-Based Simulation,
arxiv, 2025.02. [Paper] -
ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding,
arxiv, 2025.10. [Paper] -
Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas,
ACM, 2025.02. [Paper]
-
YuLan-OneSim — A large-scale LLM-based social simulator that supports code-free scenario construction, distributed execution, and simulations with up to 100K agents across multiple social-science domains.
[Paper] [Code] [Docs] -
MiroFish — A multi-agent prediction engine that builds a parallel digital world from seed information (news, policies, financial signals) and simulates agent interactions for forecasting and scenario analysis.
[Code] [Demo] -
SocioVerse — A social world simulator powered by LLM agents and a large-scale user pool, designed to simulate social dynamics across domains such as economics, politics, and media.
[Paper] [Code] -
OASIS — An open-source large-scale social interaction simulator that models dynamic online platforms and supports simulations with millions of agents.
[Paper] [Code] -
Global Economic Model [Link]
If you find this repository helpful, please consider starring it ⭐ and citing:
@misc{econwm2026econwmpaperslist,
title = {Awesome-Econ-World-Models},
author = {Jiale Han and Jing Qian and Chengrui Zhang and Wenyuan Gu and Benyou Wang},
journal = {GitHub repository},
url = {https://github.com/FreedomIntelligence/Awesome-Econ-World-Models},
year = {2026}
}
We welcome contributions on papers, projects, benchmarks, tutorials, and blog posts. Please feel free to open an issue if you would like to add relevant resources.