IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2510.17393.html
   My bibliography  Save this paper

3S-Trader: A Multi-LLM Framework for Adaptive Stock Scoring, Strategy, and Selection in Portfolio Optimization

Author

Listed:
  • Kefan Chen
  • Hussain Ahmad
  • Diksha Goel
  • Claudia Szabo

Abstract

Large Language Models (LLMs) have recently gained popularity in stock trading for their ability to process multimodal financial data. However, most existing methods focus on single-stock trading and lack the capacity to reason over multiple candidates for portfolio construction. Moreover, they typically lack the flexibility to revise their strategies in response to market shifts, limiting their adaptability in real-world trading. To address these challenges, we propose 3S-Trader, a training-free framework that incorporates scoring, strategy, and selection modules for stock portfolio construction. The scoring module summarizes each stock's recent signals into a concise report covering multiple scoring dimensions, enabling efficient comparison across candidates. The strategy module analyzes historical strategies and overall market conditions to iteratively generate an optimized selection strategy. Based on this strategy, the selection module identifies and assembles a portfolio by choosing stocks with higher scores in relevant dimensions. We evaluate our framework across four distinct stock universes, including the Dow Jones Industrial Average (DJIA) constituents and three sector-specific stock sets. Compared with existing multi-LLM frameworks and time-series-based baselines, 3S-Trader achieves the highest accumulated return of 131.83% on DJIA constituents with a Sharpe ratio of 0.31 and Calmar ratio of 11.84, while also delivering consistently strong results across other sectors.

Suggested Citation

  • Kefan Chen & Hussain Ahmad & Diksha Goel & Claudia Szabo, 2025. "3S-Trader: A Multi-LLM Framework for Adaptive Stock Scoring, Strategy, and Selection in Portfolio Optimization," Papers 2510.17393, arXiv.org.
  • Handle: RePEc:arx:papers:2510.17393
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2510.17393
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Statman, Meir, 1987. "How Many Stocks Make a Diversified Portfolio?," Journal of Financial and Quantitative Analysis, Cambridge University Press, vol. 22(3), pages 353-363, September.
    2. Yiyao Zhang & Diksha Goel & Hussain Ahmad & Claudia Szabo, 2025. "RegimeFolio: A Regime Aware ML System for Sectoral Portfolio Optimization in Dynamic Markets," Papers 2510.14986, arXiv.org.
    3. 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.
    4. Bollerslev, Tim, 1986. "Generalized autoregressive conditional heteroskedasticity," Journal of Econometrics, Elsevier, vol. 31(3), pages 307-327, April.
    5. Fischer, Thomas & Krauss, Christopher, 2018. "Deep learning with long short-term memory networks for financial market predictions," European Journal of Operational Research, Elsevier, vol. 270(2), pages 654-669.
    6. Xiao-Yang Liu & Guoxuan Wang & Hongyang Yang & Daochen Zha, 2023. "FinGPT: Democratizing Internet-scale Data for Financial Large Language Models," Papers 2307.10485, arXiv.org, revised Nov 2023.
    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. Rui Pedro Brito & Hélder Sebastião & Pedro Godinho, 2015. "Portfolio Management With Higher Moments: The Cardinality Impact," GEMF Working Papers 2015-15, GEMF, Faculty of Economics, University of Coimbra.
    2. Amin Aminimehr & Ali Raoofi & Akbar Aminimehr & Amirhossein Aminimehr, 2022. "A Comprehensive Study of Market Prediction from Efficient Market Hypothesis up to Late Intelligent Market Prediction Approaches," Computational Economics, Springer;Society for Computational Economics, vol. 60(2), pages 781-815, August.
    3. Wang, Yijun & Andreeva, Galina & Martin-Barragan, Belen, 2023. "Machine learning approaches to forecasting cryptocurrency volatility: Considering internal and external determinants," International Review of Financial Analysis, Elsevier, vol. 90(C).
    4. Jingyi Wei & Steve Yang & Zhenyu Cui, 2025. "Integrated GARCH-GRU in Financial Volatility Forecasting," Papers 2504.09380, arXiv.org.
    5. Xing Wang & Yijun Wang & Bin Weng & Aleksandr Vinel, 2020. "Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network," Papers 2010.01197, arXiv.org.
    6. Ghaemi Asl, Mahdi & Rashidi, Muhammad Mahdi & Tavakkoli, Hamid Raza & Rezgui, Hichem, 2024. "Does Islamic investing modify portfolio performance? Time-varying optimization strategies for conventional and Shariah energy-ESG-utilities portfolio," The Quarterly Review of Economics and Finance, Elsevier, vol. 94(C), pages 37-57.
    7. Frédy Pokou & Jules Sadefo Kamdem & François Benhmad, 2024. "Hybridization of ARIMA with Learning Models for Forecasting of Stock Market Time Series," Computational Economics, Springer;Society for Computational Economics, vol. 63(4), pages 1349-1399, April.
    8. Kansuda Pankwaen & Sukrit Thongkairat & Worrawat Saijai, 2025. "Global Cross-Market Trading Optimization Using Iterative Combined Algorithm: A Multi-Asset Approach with Stocks and Cryptocurrencies," Mathematics, MDPI, vol. 13(8), pages 1-27, April.
    9. Linyan Ruan & Haiwei Jiang, 2025. "Stock Price Prediction Using FinBERT-Enhanced Sentiment with SHAP Explainability and Differential Privacy," Mathematics, MDPI, vol. 13(17), pages 1-22, August.
    10. Ao Yang & Qing Ye & Jia Zhai, 2024. "Volatility forecasting with Hybrid‐long short‐term memory models: Evidence from the COVID‐19 period," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 29(3), pages 2766-2786, July.
    11. Kasper Johansson & Stephen Boyd, 2024. "Simple and Effective Portfolio Construction with Crypto Assets," Papers 2412.02654, arXiv.org.
    12. Roy Cerqueti & Mario Maggi & Jessica Riccioni, 2024. "Statistical methods for decision support systems in finance: how Benford’s law predicts financial risk," Annals of Operations Research, Springer, vol. 342(3), pages 1445-1469, November.
    13. Iwao Maeda & David deGraw & Michiharu Kitano & Hiroyasu Matsushima & Hiroki Sakaji & Kiyoshi Izumi & Atsuo Kato, 2020. "Deep Reinforcement Learning in Agent Based Financial Market Simulation," JRFM, MDPI, vol. 13(4), pages 1-17, April.
    14. Andrés García-Medina & Ester Aguayo-Moreno, 2024. "LSTM–GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency Portfolios," Computational Economics, Springer;Society for Computational Economics, vol. 63(4), pages 1511-1542, April.
    15. Jakub Micha'nk'ow & {L}ukasz Kwiatkowski & Janusz Morajda, 2023. "Combining Deep Learning and GARCH Models for Financial Volatility and Risk Forecasting," Papers 2310.01063, arXiv.org.
    16. Gupta, Abhijit, 2025. "Decoding Futures Price Dynamics: A Regularized Sparse Autoencoder for Interpretable Multi-Horizon Forecasting and Factor Discovery," OSF Preprints 4rzky_v1, Center for Open Science.
    17. Taylor, Nicholas, 2008. "Can idiosyncratic volatility help forecast stock market volatility?," International Journal of Forecasting, Elsevier, vol. 24(3), pages 462-479.
    18. Hyungjun Park & Min Kyu Sim & Dong Gu Choi, 2019. "An intelligent financial portfolio trading strategy using deep Q-learning," Papers 1907.03665, arXiv.org, revised Nov 2019.
    19. Ngo, Vu Minh & Nguyen, Huan Huu & Van Nguyen, Phuc, 2023. "Does reinforcement learning outperform deep learning and traditional portfolio optimization models in frontier and developed financial markets?," Research in International Business and Finance, Elsevier, vol. 65(C).
    20. Weiguo Zhang & Xue Gong & Chao Wang & Xin Ye, 2021. "Predicting stock market volatility based on textual sentiment: A nonlinear analysis," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(8), pages 1479-1500, December.

    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:2510.17393. 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.