IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2511.12876.html

Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making

Author

Listed:
  • Heyang Ma
  • Qirui Mi
  • Qipeng Yang
  • Zijun Fan
  • Bo Li
  • Haifeng Zhang

Abstract

Economic decision-making depends not only on structured signals such as prices and taxes, but also on unstructured language, including peer dialogue and media narratives. While multi-agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic ambiguity and contextual richness of language. We propose LAMP (Language-Augmented Multi-Agent Policy), a framework that integrates language into economic decision-making and narrows the gap to real-world settings. LAMP follows a Think-Speak-Decide pipeline: (1) Think interprets numerical observations to extract short-term shocks and long-term trends, caching high-value reasoning trajectories; (2) Speak crafts and exchanges strategic messages based on reasoning, updating beliefs by parsing peer communications; and (3) Decide fuses numerical data, reasoning, and reflections into a MARL policy to optimize language-augmented decision-making. Experiments in economic simulation show that LAMP outperforms both MARL and LLM-only baselines in cumulative return (+63.5%, +34.0%), robustness (+18.8%, +59.4%), and interpretability. These results demonstrate the potential of language-augmented policies to deliver more effective and robust economic strategies.

Suggested Citation

  • Heyang Ma & Qirui Mi & Qipeng Yang & Zijun Fan & Bo Li & Haifeng Zhang, 2025. "Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making," Papers 2511.12876, arXiv.org, revised Dec 2025.
  • Handle: RePEc:arx:papers:2511.12876
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2511.12876
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Fatih Ozhamaratli & Paolo Barucca, 2022. "Deep Reinforcement Learning for Optimal Investment and Saving Strategy Selection in Heterogeneous Profiles: Intelligent Agents working towards retirement," Papers 2206.05835, arXiv.org.
    2. Tohid Atashbar & Rui Aruhan Shi, 2023. "AI and Macroeconomic Modeling: Deep Reinforcement Learning in an RBC model," IMF Working Papers 2023/040, International Monetary Fund.
    3. Mingli Chen & Andreas Joseph & Michael Kumhof & Xinlei Pan & Xuan Zhou, 2021. "Deep Reinforcement Learning in a Monetary Model," Papers 2104.09368, arXiv.org, revised Jan 2023.
    4. Arthur Charpentier & Romuald Élie & Carl Remlinger, 2023. "Reinforcement Learning in Economics and Finance," Computational Economics, Springer;Society for Computational Economics, vol. 62(1), pages 425-462, June.
    5. Rui (Aruhan) Shi, 2021. "Learning from Zero: How to Make Consumption-Saving Decisions in a Stochastic Environment with an AI Algorithm," CESifo Working Paper Series 9255, CESifo.
    6. Edward Hill & Marco Bardoscia & Arthur Turrell, 2021. "Solving Heterogeneous General Equilibrium Economic Models with Deep Reinforcement Learning," Papers 2103.16977, arXiv.org.
    7. John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," NBER Working Papers 31122, National Bureau of Economic Research, Inc.
    8. John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," Papers 2301.07543, arXiv.org.
    9. Artem Kuriksha, 2021. "An Economy of Neural Networks: Learning from Heterogeneous Experiences," Papers 2110.11582, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Qirui Mi & Zhiyu Zhao & Chengdong Ma & Siyu Xia & Yan Song & Mengyue Yang & Jun Wang & Haifeng Zhang, 2024. "Learning Macroeconomic Policies through Dynamic Stackelberg Mean-Field Games," Papers 2403.12093, arXiv.org, revised Jun 2025.
    2. Simone Brusatin & Tommaso Padoan & Andrea Coletta & Domenico Delli Gatti & Aldo Glielmo, 2024. "Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modelling," Papers 2405.02161, arXiv.org, revised Oct 2024.
    3. Qirui Mi & Qipeng Yang & Zijun Fan & Wentian Fan & Heyang Ma & Chengdong Ma & Siyu Xia & Bo An & Jun Wang & Haifeng Zhang, 2025. "EconGym: A Scalable AI Testbed with Diverse Economic Tasks," Papers 2506.12110, arXiv.org.
    4. Iñaki Aldasoro & Ajit Desai, 2025. "Money Talks: AI Agents for Cash Management in Payment Systems," Staff Working Papers 25-35, Bank of Canada.
    5. Kevin Leyton-Brown & Paul Milgrom & Neil Newman & Ilya Segal, 2024. "Artificial Intelligence and Market Design: Lessons Learned from Radio Spectrum Reallocation," NBER Chapters, in: New Directions in Market Design, National Bureau of Economic Research, Inc.
    6. C. Monica Capra & Thomas J. Kniesner, 2025. "Daniel Kahneman’s underappreciated last published paper: Empirical implications for benefit-cost analysis and a chat session discussion with bots," Journal of Risk and Uncertainty, Springer, vol. 71(1), pages 29-51, August.
    7. Kirshner, Samuel N., 2024. "GPT and CLT: The impact of ChatGPT's level of abstraction on consumer recommendations," Journal of Retailing and Consumer Services, Elsevier, vol. 76(C).
    8. Shu Wang & Zijun Yao & Shuhuai Zhang & Jianuo Gai & Tracy Xiao Liu & Songfa Zhong, 2025. "When Experimental Economics Meets Large Language Models: Evidence-based Tactics," Papers 2505.21371, arXiv.org, revised Jul 2025.
    9. Koji Takahashi & Joon Suk Park, 2025. "Generative AI for Surveys on Payment Apps: AIs' View on Privacy and Technology," IMES Discussion Paper Series 25-E-13, Institute for Monetary and Economic Studies, Bank of Japan.
    10. Zengqing Wu & Run Peng & Xu Han & Shuyuan Zheng & Yixin Zhang & Chuan Xiao, 2023. "Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations," Papers 2311.06330, arXiv.org, revised Dec 2023.
    11. repec:osf:osfxxx:udz28_v1 is not listed on IDEAS
    12. Hui Chen & Antoine Didisheim & Luciano Somoza & Hanqing Tian, 2025. "A Financial Brain Scan of the LLM," Papers 2508.21285, arXiv.org.
    13. Joshua C. Yang & Damian Dailisan & Marcin Korecki & Carina I. Hausladen & Dirk Helbing, 2024. "LLM Voting: Human Choices and AI Collective Decision Making," Papers 2402.01766, arXiv.org, revised Aug 2024.
    14. Elif Akata & Lion Schulz & Julian Coda-Forno & Seong Joon Oh & Matthias Bethge & Eric Schulz, 2025. "Playing repeated games with large language models," Nature Human Behaviour, Nature, vol. 9(7), pages 1380-1390, July.
    15. Nir Chemaya & Daniel Martin, 2024. "Perceptions and detection of AI use in manuscript preparation for academic journals," PLOS ONE, Public Library of Science, vol. 19(7), pages 1-16, July.
    16. Lijia Ma & Xingchen Xu & Yong Tan, 2024. "Crafting Knowledge: Exploring the Creative Mechanisms of Chat-Based Search Engines," Papers 2402.19421, arXiv.org.
    17. Ali Goli & Amandeep Singh, 2023. "Exploring the Influence of Language on Time-Reward Perceptions in Large Language Models: A Study Using GPT-3.5," Papers 2305.02531, arXiv.org, revised Jun 2023.
    18. repec:osf:osfxxx:r3qng_v1 is not listed on IDEAS
    19. Evangelos Katsamakas, 2024. "Business models for the simulation hypothesis," Papers 2404.08991, arXiv.org.
    20. Yuan Gao & Dokyun Lee & Gordon Burtch & Sina Fazelpour, 2024. "Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina," Papers 2410.19599, arXiv.org, revised Jan 2025.
    21. Umberto Collodel, 2025. "Interpreting the Interpreter: Can We Model post-ECB Conferences Volatility with LLM Agents?," Papers 2508.13635, arXiv.org, revised Oct 2025.
    22. Matthew O. Jackson & Qiaozhu Me & Stephanie W. Wang & Yutong Xie & Walter Yuan & Seth Benzell & Erik Brynjolfsson & Colin F. Camerer & James Evans & Brian Jabarian & Jon Kleinberg & Juanjuan Meng & Se, 2025. "AI Behavioral Science," Papers 2509.13323, arXiv.org.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2511.12876. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.