IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2605.23007.html

MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models

Author

Listed:
  • Yurii Kvasiuk
  • Tianyi Li
  • Owen Colegrove
  • Moritz Munchmeyer

Abstract

We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorithm optimization framework inspired by DeepMind's Alpha-Evolve, was recently developed to optimize algorithms in computational cosmology. Here we demonstrate the utility of MadEvolve to optimize algorithmic trading strategies and alpha generation at the example of Bitcoin trading. On our simulation and backtesting setup, we achieve significant improvements on all tasks we considered, such as evolving feature sets for signal generation, optimizing separate components of the trading strategy, and jointly evolving the feature pipeline together with the execution strategy. Additionally, we compare our method to other agentic search approaches, specifically Claude Code, and carefully evaluate p-hacking probabilities on our simulation setup. Our findings strongly support the utility of AI-driven agentic and evolutionary algorithms for algorithmic trading and quantitative finance.

Suggested Citation

  • Yurii Kvasiuk & Tianyi Li & Owen Colegrove & Moritz Munchmeyer, 2026. "MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models," Papers 2605.23007, arXiv.org.
    • Handle: RePEc:arx:papers:2605.23007
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2605.23007
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jean Lee & Nicholas Stevens & Soyeon Caren Han & Minseok Song, 2024. "A Survey of Large Language Models in Finance (FinLLMs)," Papers 2402.02315, arXiv.org.
    2. 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.
    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. Kunihiro Miyazaki & Takanobu Kawahara & Stephen Roberts & Stefan Zohren, 2026. "Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks," Papers 2602.23330, arXiv.org.
    2. Benjamin Coriat & Eric Benhamou, 2025. "HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization," Papers 2507.18560, arXiv.org.
    3. Tirulo, Aschalew & Yadav, Monika & Lolamo, Mathewos & Chauhan, Siddhartha & Siano, Pierluigi & Shafie-khah, Miadreza, 2026. "Beyond automation: Unveiling the potential of agentic intelligence," Renewable and Sustainable Energy Reviews, Elsevier, vol. 226(PA).
    4. Mehmet Caner & Agostino Capponi & Nathan Sun & Jonathan Y. Tan, 2026. "Designing Agentic AI-Based Screening for Portfolio Investment," Papers 2603.23300, arXiv.org.
    5. Zhi Yang & Lingfeng Zeng & Fangqi Lou & Qi Qi & Wei Zhang & Zhenyu Wu & Zhenxiong Yu & Jun Han & Zhiheng Jin & Lejie Zhang & Xiaoming Huang & Xiaolong Liang & Zheng Wei & Junbo Zou & Dongpo Cheng & Zh, 2026. "UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos," Papers 2601.22162, arXiv.org.
    6. Hamidou Tembine & Manzoor Ahmed Khan & Issa Bamia, 2024. "Mean-Field-Type Transformers," Mathematics, MDPI, vol. 12(22), pages 1-51, November.
    7. Olivia Zhang & Zhilin Zhang, 2026. "A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective," Papers 2605.05211, arXiv.org.
    8. Kassiani Papasotiriou & Srijan Sood & Shayleen Reynolds & Tucker Balch, 2024. "AI in Investment Analysis: LLMs for Equity Stock Ratings," Papers 2411.00856, arXiv.org.
    9. Junhua Liu, 2024. "A Survey of Financial AI: Architectures, Advances and Open Challenges," Papers 2411.12747, arXiv.org.
    10. Aadi Singhi, 2025. "An Adaptive Multi Agent Bitcoin Trading System," Papers 2510.08068, arXiv.org, revised Nov 2025.
    11. Maxime Saxena & Marco Pangallo & Cars Hommes & Fabio Caccioli & R. Maria del Rio-Chanona, 2026. "Machine Spirits: Speculation and Adaptation of LLM Agents in Asset Markets," Papers 2604.18602, arXiv.org, revised Apr 2026.
    12. Simeon Allmendinger & Lukas Bonenberger & Kathrin Endres & Dominik Fetzer & Henner Gimpel & Niklas Kühl, 2026. "Multi-agent AI," Electronic Markets, Springer;IIM University of St. Gallen, vol. 36(1), pages 1-18, December.
    13. Haoyi Zhang & Tianyi Zhu, 2025. "Neither Consent nor Property: A Policy Lab for Data Law," Papers 2510.26727, arXiv.org, revised Apr 2026.
    14. Satyadhar Joshi, 2025. "Review of Gen AI Models for Financial Risk Management: Architectural Frameworks and Implementation Strategies," Post-Print hal-05101589, HAL.
    15. Weixian Waylon Li & Hyeonjun Kim & Mihai Cucuringu & Tiejun Ma, 2025. "Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?," Papers 2505.07078, arXiv.org, revised Jun 2026.
    16. Han Ding & Yinheng Li & Junhao Wang & Hang Chen & Doudou Guo & Yunbai Zhang, 2024. "Large Language Model Agent in Financial Trading: A Survey," Papers 2408.06361, arXiv.org, revised Mar 2026.
    17. Yaxuan Kong & Hoyoung Lee & Yoontae Hwang & Alejandro Lopez-Lira & Bradford Levy & Dhagash Mehta & Qingsong Wen & Chanyeol Choi & Yongjae Lee & Stefan Zohren, 2026. "Evaluating LLMs in Finance Requires Explicit Bias Consideration," Papers 2602.14233, arXiv.org.

    More about this item

    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:2605.23007. 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.