IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2606.08283.html

Macro Economists in the Machine: A Multi-Agent LLM Framework for Commodity-Related ETF Portfolio Construction

Author

Listed:
  • Yiqing Wang
  • Dehao Dai
  • Ding Ma
  • Kerui Geng

Abstract

We test whether large language models (LLMs) add value in commodity portfolio construction when the information set and implementation rules are held fixed across strategies. A Hawkish Agent (inflation-tightening prior), a Dovish Agent (growth-easing prior), a Debate Agent, and a deterministic z-score Rule Agent each receive identical FRED macro z-scores and route their tilt signals through the same portfolio engine. Across 124 weekly rebalancing dates spanning the 2023 U.S. rate peak and the 2024-2025 soft landing, all three LLM strategies outperform the Rule Agent in Sharpe terms; the Hawkish and Debate Agents record the largest gains (\Delta Sharpe = +0.044 and +0.040, both p

Suggested Citation

  • Yiqing Wang & Dehao Dai & Ding Ma & Kerui Geng, 2026. "Macro Economists in the Machine: A Multi-Agent LLM Framework for Commodity-Related ETF Portfolio Construction," Papers 2606.08283, arXiv.org.
    • Handle: RePEc:arx:papers:2606.08283
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2606.08283
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Victor DeMiguel & Lorenzo Garlappi & Francisco J. Nogales & Raman Uppal, 2009. "A Generalized Approach to Portfolio Optimization: Improving Performance by Constraining Portfolio Norms," Management Science, INFORMS, vol. 55(5), pages 798-812, May.
    2. Gurdip Bakshi & Xiaohui Gao & Alberto G. Rossi, 2019. "Understanding the Sources of Risk Underlying the Cross Section of Commodity Returns," Management Science, INFORMS, vol. 65(2), pages 619-641, February.
    3. Claude B. Erb & Campbell R. Harvey, 2015. "The Strategic and Tactical Value of Commodity Futures," World Scientific Book Chapters, in: Anastasios G Malliaris & William T Ziemba (ed.), THE WORLD SCIENTIFIC HANDBOOK OF FUTURES MARKETS, chapter 6, pages 125-178, World Scientific Publishing Co. Pte. Ltd..
    4. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," Review of Finance, European Finance Association, vol. 33(5), pages 2223-2273.
    5. Joseph P. Romano & Michael Wolf, 2005. "Stepwise Multiple Testing as Formalized Data Snooping," Econometrica, Econometric Society, vol. 73(4), pages 1237-1282, July.
    6. Marta Szymanowska & Frans Roon & Theo Nijman & Rob Goorbergh, 2014. "An Anatomy of Commodity Futures Risk Premia," Journal of Finance, American Finance Association, vol. 69(1), pages 453-482, February.
    7. Hansen, Peter Reinhard, 2005. "A Test for Superior Predictive Ability," Journal of Business & Economic Statistics, American Statistical Association, vol. 23, pages 365-380, October.
    8. Gary Gorton & K. Geert Rouwenhorst, 2006. "Facts and Fantasies about Commodity Futures," Financial Analysts Journal, Taylor & Francis Journals, vol. 62(2), pages 47-68, March.
    9. Ke Tang & Wei Xiong, 2012. "Index Investment and the Financialization of Commodities," Financial Analysts Journal, Taylor & Francis Journals, vol. 68(6), pages 54-74, November.
    10. Zhengyao Jiang & Dixing Xu & Jinjun Liang, 2017. "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem," Papers 1706.10059, arXiv.org, revised Jul 2017.
    11. Gary B. Gorton & Fumio Hayashi & K. Geert Rouwenhorst, 2013. "The Fundamentals of Commodity Futures Returns," Review of Finance, European Finance Association, vol. 17(1), pages 35-105.
    12. Dehao Dai & Ding Ma & Dou Liu & Kerui Geng & Yiqing Wang, 2026. "Beyond Polarity: Multi-Dimensional LLM Sentiment Signals for WTI Crude Oil Futures Return Prediction," Papers 2603.11408, arXiv.org, revised Mar 2026.
    13. Daskalaki, Charoula & Kostakis, Alexandros & Skiadopoulos, George, 2014. "Are there common factors in individual commodity futures returns?," Journal of Banking & Finance, Elsevier, vol. 40(C), pages 346-363.
    14. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," The Review of Financial Studies, Society for Financial Studies, vol. 33(5), pages 2223-2273.
    15. Tianjiao Zhao & Jingrao Lyu & Stokes Jones & Harrison Garber & Stefano Pasquali & Dhagash Mehta, 2025. "AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions," Papers 2508.11152, arXiv.org.
    16. Joseph P. Romano & Michael Wolf, 2005. "Exact and Approximate Stepdown Methods for Multiple Hypothesis Testing," Journal of the American Statistical Association, American Statistical Association, vol. 100, pages 94-108, March.
    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. Rad, Hossein & Low, Rand Kwong Yew & Miffre, Joëlle & Faff, Robert, 2023. "The commodity risk premium and neural networks," Journal of Empirical Finance, Elsevier, vol. 74(C).
    2. Angelidis, Timotheos & Sakkas, Athanasios & Tessaromatis, Nikolaos, 2025. "Predicting commodity returns: Time series vs. cross sectional prediction models," Journal of Commodity Markets, Elsevier, vol. 38(C).
    3. Nakagawa, Kei & Sakemoto, Ryuta, 2024. "Commodity sectors and factor investment strategies," International Review of Financial Analysis, Elsevier, vol. 95(PC).
    4. Melone, Alessandro & Randl, Otto & Sögner, Leopold & Zechner, Josef, 2025. "Stock-Oil Comovement: Cash Flows or Discount Rates?," VfS Annual Conference 2025 (Cologne): Revival of Industrial Policy 325398, Verein für Socialpolitik / German Economic Association.
    5. Shirui Wang & Tianyang Zhang, 2024. "Predictability of commodity futures returns with machine learning models," Journal of Futures Markets, John Wiley & Sons, Ltd., vol. 44(2), pages 302-322, February.
    6. Fan, John Hua & Fernandez-Perez, Adrian & Indriawan, Ivan & Todorova, Neda, 2024. "When Chinese mania meets global frenzy: Commodity price bubbles," Journal of Commodity Markets, Elsevier, vol. 36(C).
    7. John Hua Fan & Tingxi Zhang, 2020. "The untold story of commodity futures in China," Journal of Futures Markets, John Wiley & Sons, Ltd., vol. 40(4), pages 671-706, April.
    8. Coqueret, Guillaume & Tavin, Bertrand & Zhou, Yuxin, 2026. "Sustainability in commodity markets," Journal of Banking & Finance, Elsevier, vol. 184(C).
    9. Chi, Yeguang & El-Jahel, Lina & Vu, Thanh, 2025. "Media emotion intensity and commodity futures pricing," Journal of Commodity Markets, Elsevier, vol. 37(C).
    10. Wang, Qiao & Balvers, Ronald, 2021. "Determinants and predictability of commodity producer returns," Journal of Banking & Finance, Elsevier, vol. 133(C).
    11. Daxuan Cheng & Yin Liao & Zheyao Pan, 2023. "The geopolitical risk premium in the commodity futures market," Journal of Futures Markets, John Wiley & Sons, Ltd., vol. 43(8), pages 1069-1090, August.
    12. Isleimeyyeh, Mohammad, 2025. "Financial investors and cross-commodity markets integration," Journal of Commodity Markets, Elsevier, vol. 38(C).
    13. Cortazar, Gonzalo & Ortega, Hector & Rojas, Maximiliano & Schwartz, Eduardo S., 2021. "Commodity index risk premium," Journal of Commodity Markets, Elsevier, vol. 22(C).
    14. Petropoulos, Fotios & Apiletti, Daniele & Assimakopoulos, Vassilios & Babai, Mohamed Zied & Barrow, Devon K. & Ben Taieb, Souhaib & Bergmeir, Christoph & Bessa, Ricardo J. & Bijak, Jakub & Boylan, Joh, 2022. "Forecasting: theory and practice," International Journal of Forecasting, Elsevier, vol. 38(3), pages 705-871.
      • Fotios Petropoulos & Daniele Apiletti & Vassilios Assimakopoulos & Mohamed Zied Babai & Devon K. Barrow & Souhaib Ben Taieb & Christoph Bergmeir & Ricardo J. Bessa & Jakub Bijak & John E. Boylan & Jet, 2020. "Forecasting: theory and practice," Papers 2012.03854, arXiv.org, revised Jan 2022.
    15. Li, Hemei & Liu, Zhenya & Zhao, Yuqian, 2023. "The Fortune and crash of common risk factors in Chinese commodity markets," Journal of Commodity Markets, Elsevier, vol. 32(C).
    16. Immo Stadtmüller & Benjamin R. Auer & Frank Schuhmacher, 2024. "Core-satellite investing with commodity futures momentum," Journal of Asset Management, Palgrave Macmillan, vol. 25(3), pages 261-287, May.
    17. Alexander Sheppert, 2026. "The GT-Score: A Robust Objective Function for Reducing Overfitting in Data-Driven Trading Strategies," Papers 2602.00080, arXiv.org.
    18. Pan, Zhiyuan & Zhong, Hao & Wang, Yudong & Huang, Juan, 2024. "Forecasting oil futures returns with news," Energy Economics, Elsevier, vol. 134(C).
    19. Sakkas, Athanasios & Tessaromatis, Nikolaos, 2020. "Factor based commodity investing," Journal of Banking & Finance, Elsevier, vol. 115(C).
    20. Aoxin Zhang & Yuhan Cheng & Kwanting Leung, 2026. "Benchmarking Deep Time Series Models for Equity Portfolios," Papers 2606.09420, 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:2606.08283. 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: https://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.