Elamur Research⌕
☰
home / papers / 2024 / EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities

EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities

Paper · 2024 · Nian Li, Chen Gao, Mingyu Li et al.

Summary

Agent-based models (ABM) of the economy usually drive households with hand-written rules or trained neural networks. Under both approaches, giving each agent its own decision logic is hard, and agents rarely consider how past market conditions should shape their choices. The authors propose EconAgent, in which a large language model makes household decisions within a month-by-month simulation. The environment includes:

  • labor and consumption markets,
  • progressive income tax based on the 2018 U.S. federal brackets, with revenue shared equally,
  • wages and prices that adjust to supply–demand gaps,
  • a bank that sets interest via the Taylor rule.

A perception module gives every agent a realistic profile (name, age, job). A memory module lets agents reflect on their own history and on market trends. With this context, each agent decides whether to work and what share of its wealth to spend. Compared with rule-based and learning-based baselines, the simulations yield more plausible inflation and unemployment behavior, and agents react to shocks in human-like ways. This makes the work an early bridge between LLM agents and macroeconomic modeling.

Key points

  • Agent decisions: Each simulation step is one month. Agents choose a work propensity (sampled as a Bernoulli outcome) and a consumption propensity.
  • Wages and population: Hourly wages follow a Pareto distribution, and monthly pay assumes 168 working hours. Agent ages mirror the 2018 U.S. population aged 18–60.
  • Monetary policy: Once a year, the bank resets the interest rate with the Taylor rule, using annual inflation and unemployment as inputs. Savings earn interest annually.
  • COVID-19 test: Adding a prompt about the national emergency (from March 2020) reproduced the jump in unemployment in 2020 Q1 qualitatively, though not the exact real-world values. Because no government relief measures were modeled, unemployment stayed elevated afterwards.
  • Limitations and code: Firms, other taxes, policy optimization and forecasting are left for future work. Code is available at github.com/tsinghua-fib-lab/ACL24-EconAgent.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Tsinghua UniversityBeijing · China333 works · 87,019 citations🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China28 works · 3,035 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksDecision Sciences · 209 worksManagement Science and Operations Research · 108 worksEconomics, Econometrics and Finance · 17 worksEconomics and Econometrics · 12 works

Cite

Cite as Nian Li, Chen Gao, Mingyu Li, Yong Li and Qingmin Liao. 2024. EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.acl-long.829

@inproceedings{li2024econagent,
  title = {{EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities}},
  author = {Nian Li, Chen Gao, Mingyu Li, Yong Li and Qingmin Liao},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2024},
  doi = {10.18653/v1/2024.acl-long.829},
  url = {https://doi.org/10.18653/v1/2024.acl-long.829}
}

References

51 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Elif Akata, Lion Schulz, Julian Coda-Forno, Seong Joon Oh, Matthias Bethge, and Eric Schulz. 2023. Playing repeated games with large language models. arXiv preprint arXiv:2305.16867. — [arXiv:2305.16867](https://arxiv.org/abs/2305.16867) find
  2. Anonymous. 2024. Rethinking the buyer’s inspection paradox in information markets with language agents. find
  3. Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, and Anil Anthony Bharath. 2017. Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine, 34(6):26–38. find
  4. Robert L Axtell and J Doyne Farmer. 2022. Agent-based modeling in economics and finance: Past, present, and future. Journal of Economic Literature. find
  5. Daniil A Boiko, Robert MacKnight, and Gabe Gomes. 2023. Emergent autonomous scientific research capabilities of large language models. arXiv preprint arXiv:2304.05332. find
  6. Andres M Bran, Sam Cox, Andrew D White, and Philippe Schwaller. 2023. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376. find
  7. William A Brock and Cars H Hommes. 1998. Heterogeneous beliefs and routes to chaos in a simple asset pricing model. Journal of Economic dynamics and Control, 22(8-9):1235–1274. find
  8. US Census Bureau. 2024. Access demographic, economic and population data from the u.s. census bureau. find
  9. Christophe Deissenberg, Sander Van Der Hoog, and Herbert Dawid. 2008. Eurace: A massively parallel agent-based model of the european economy. Applied mathematics and computation, 204(2):541– 552. find
  10. Jingtao Ding, Chang Liu, Yu Zheng, Yunke Zhang, Zihan Yu, Ruikun Li, Hongyi Chen, Jinghua Piao, Huandong Wang, Jiazhen Liu, et al. 2024. Artificial intelligence for complex network: Potential, methodology and application. arXiv preprint arXiv:2402.16887. — [arXiv:2402.16887](https://arxiv.org/abs/2402.16887) find
  11. J Doyne Farmer and Duncan Foley. 2009. The economy needs agent-based modelling. Nature, 460(7256):685–686. find
  12. Chen Gao, Xiaochong Lan, Nian Li, Yuan Yuan, Jingtao Ding, Zhilun Zhou, Fengli Xu, and Yong Li. 2023a. Large language models empowered agent-based modeling and simulation: A survey and perspectives. arXiv preprint arXiv:2312.11970. find
  13. Chen Gao, Xiaochong Lan, Zhihong Lu, Jinzhu Mao, Jinghua Piao, Huandong Wang, Depeng Jin, and Yong Li. 2023b. S 3 : Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984. — [arXiv:2307.14984](https://arxiv.org/abs/2307.14984) find
  14. Domenico Delli Gatti, Saul Desiderio, Edoardo Gaffeo, Pasquale Cirillo, and Mauro Gallegati. 2011. Macroeconomics from the Bottom-up, volume 1. Springer Science & Business Media. find
  15. Nigel Gilbert and Klaus Troitzsch. 2005. Simulation for the social scientist. McGraw-Hill Education (UK). find
  16. Fulin Guo. 2023. Gpt agents in game theory experiments. arXiv preprint arXiv:2305.05516. — [arXiv:2305.05516](https://arxiv.org/abs/2305.05516) find
  17. Christopher D Carroll. 1997. Buffer-stock saving and the life cycle/permanent income hypothesis. The Quarterly journal of economics, 112(1):1–55. find
  18. David F Hendry and Jean-Francois Richard. 1982. On the formulation of empirical models in dynamic econometrics. Journal of Econometrics, 20(1):3–33. find
  19. Jiangjie Chen, Siyu Yuan, Rong Ye, Bodhisattwa Prasad Majumder, and Kyle Richardson. 2023a. Put your money where your mouth is: Evaluating strategic planning and execution of llm agents in an auction arena. arXiv preprint arXiv:2310.05746. — [arXiv:2310.05746](https://arxiv.org/abs/2310.05746) find
  20. John J Horton. 2023. Large language models as simulated economic agents: What can we learn from homo silicus? Technical report, National Bureau of Economic Research. find
  21. Yiting Chen, Tracy Xiao Liu, You Shan, and Songfa Zhong. 2023b. The emergence of economic rationality of gpt. arXiv preprint arXiv:2305.12763. — [arXiv:2305.12763](https://arxiv.org/abs/2305.12763) find
  22. Lawrence J Christiano, Martin Eichenbaum, and Charles L Evans. 2005. Nominal rigidities and the dynamic effects of a shock to monetary policy. Journal of political Economy, 113(1):1–45. find
  23. Shi Jinxin, Zhao Jiabao, Wang Yilei, Wu Xingjiao, Li Jiawen, and He Liang. 2023. Cgmi: Configurable general multi-agent interaction framework. arXiv preprint arXiv:2308.12503. — [arXiv:2308.12503](https://arxiv.org/abs/2308.12503) find
  24. Dale W Jorgenson. 2001. Information technology and the us economy. American Economic Review, 91(1):1–32. find
  25. Herbert Dawid and Domenico Delli Gatti. 2018. Agent-based macroeconomics. Handbook of computational economics, 4:63–156. find
  26. Grgur Kovač, Rémy Portelas, Peter Ford Dominey, and Pierre-Yves Oudeyer. 2023. The socialai school: Insights from developmental psychology towards artificial socio-cultural agents. arXiv preprint arXiv:2307.07871. — [arXiv:2307.07871](https://arxiv.org/abs/2307.07871) find
  27. Herbert Dawid, Simon Gemkow, Philipp Harting, Sander Van der Hoog, and Michael Neugart. 2012. The eurace@ unibi model: An agent-based macroeconomic model for economic policy analysis. find
  28. Finn E Kydland and Edward C Prescott. 1982. Time to build and aggregate fluctuations. Econometrica: Journal of the Econometric Society, pages 1345– 1370. find
  29. Matthias Lengnick. 2013. Agent-based macroeconomics: A baseline model. Journal of Economic Behavior & Organization, 86:102–120. find
  30. Leigh Tesfatsion and Kenneth L Judd. 2006. Handbook of computational economics: agent-based computational economics. Elsevier. find
  31. Qirui Mi, Siyu Xia, Yan Song, Haifeng Zhang, Shenghao Zhu, and Jun Wang. 2023. Taxai: A dynamic economic simulator and benchmark for multi-agent reinforcement learning. arXiv preprint arXiv:2309.16307. — [arXiv:2309.16307](https://arxiv.org/abs/2309.16307) find
  32. Alexander Trott, Sunil Srinivasa, Douwe van der Wal, Sebastien Haneuse, and Stephan Zheng. 2021. Building a foundation for data-driven, interpretable, and robust policy design using the ai economist. arXiv preprint arXiv:2108.02904. — [arXiv:2108.02904](https://arxiv.org/abs/2108.02904) find
  33. Arthur M Okun. 1963. Potential GNP: its measurement and significance. Cowles Foundation for Research in Economics at Yale University. find
  34. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. 2023. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432.
  35. Organization for Economic Co-operation and Development. 1970. Infra-Annual Labor Statistics: Unemployment Rate Total: From 15 to 64 Years for United States. find
  36. Joon Sung Park, Joseph C O’Brien, Carrie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442. find
  37. Joon Sung Park, Lindsay Popowski, Carrie Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2022. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pages 1–18. find
  38. Edmund S Phelps. 1967. Phillips curves, expectations of inflation and optimal unemployment over time. Economica, pages 254–281. find
  39. Sebastian Poledna, Michael Gregor Miess, Cars Hommes, and Katrin Rabitsch. 2023. Economic forecasting with an agent-based model. European Economic Review, 151:104306. find
  40. Frank Schorfheide and Dongho Song. 2015. Real-time forecasting with a mixed-frequency var. Journal of Business & Economic Statistics, 33(3):366–380. find
  41. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. find
  42. Yu Shang, Yu Li, Fengli Xu, and Yong Li. 2024. Defint: A default-interventionist framework for efficient reasoning with hybrid large language models. arXiv preprint arXiv:2402.02563. find
  43. Chenyang Shao, Fengli Xu, Bingbing Fan, Jingtao Ding, Yuan Yuan, Meng Wang, and Yong Li. 2024. Beyond imitation: Generating human mobility from context-aware reasoning with large language models. arXiv preprint arXiv:2402.09836. — [arXiv:2402.09836](https://arxiv.org/abs/2402.09836) find
  44. AutoGPT Team. 2022. Autogpt: the heart of the open-source agent ecosystem. https://github.com/ Significant-Gravitas/AutoGPT. (Accessed on 01/10/2023). ↗
  45. Paul Windrum, Giorgio Fagiolo, and Alessio Moneta. 2007. Empirical validation of agent-based models: Alternatives and prospects. Journal of Artificial Societies and Social Simulation, 10(2):8. find
  46. Sarah Wolf, Steffen Fürst, Antoine Mandel, Wiebke Lass, Daniel Lincke, Federico Pablo-Marti, and Carlo Jaeger. 2013. A multi-agent model of several economic regions. Environmental modelling & software, 44:25–43. find
  47. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  48. Yoheinakajima. 2023. Babyagi. https://github.com/yoheinakajima/babyagi. (Accessed on 01/10/2023). ↗
  49. Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, and Xing Xie. 2023a. Competeai: Understanding the competition behaviors in large language model-based agents. arXiv preprint arXiv:2310.17512. find
  50. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. 2023b. A survey of large language models. arXiv preprint arXiv:2303.18223.
  51. Stephan Zheng, Alexander Trott, Sunil Srinivasa, David C Parkes, and Richard Socher. 2022. The ai economist: Taxation policy design via two-level deep multiagent reinforcement learning. Science advances, 8(18):eabk2607. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/li-2024-econagent-large-language-model-empowered/