IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2609.27051.html

Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors

Author

Listed:
  • Bo Qu
  • Mingguang Chen
  • Licheng Wang

Abstract

Language-model agents now run the whole of quantitative factor research: they propose investment factors, backtest them, select the survivors and retire them. We ask which of those jobs an agent should keep. Our answer is governed self-evolution: the agent may propose, and a frozen statistical referee that the agent cannot touch must judge. The referee scores each candidate only on market outcomes revealed after submission, by betting, so its false-discovery guarantee holds at every stopping time for any proposal policy. We cross three proposers (a script, a bandit and a language model) with this referee and with three deliberately leaky ones, in a synthetic world with planted truth, a probe-authoring environment and a ten-year walk-forward on the CSI 500. Who judges sets the number of false admissions: the frozen referee admits 5-11 times fewer sub-threshold factors than the leaky referees under a scripted proposer, and no proposer closes that gap. Who proposes sets the yield: the language model beats the script, matches the bandit, and adds the one capability a bandit lacks, writing its own diagnostic probes. The certificate's price is time: an admitted true factor waits about 500 trading days, and the certified portfolio's Sharpe ratio therefore trails an ungated one. Judging belongs to the procedure; proposing and instrument-making belong to the agent.

Suggested Citation

  • Bo Qu & Mingguang Chen & Licheng Wang, 2026. "Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors," Papers 2609.27051, arXiv.org.
    • Handle: RePEc:arx:papers:2609.27051
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2609.27051
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yuante Li & Xu Yang & Xiao Yang & Minrui Xu & Xisen Wang & Weiqing Liu & Jiang Bian, 2025. "R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization," Papers 2505.15155, arXiv.org, revised Sep 2025.
    2. Wang, Hongjian & Dandapanthula, Sanjit & Ramdas, Aaditya, 2025. "Anytime-valid FDR control with the stopped e-BH procedure," Statistics & Probability Letters, Elsevier, vol. 226(C).
    3. Bo Qu & Mingguang Chen, 2026. "CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents," Papers 2606.29771, arXiv.org, revised Sep 2026.
    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. Yingjian Pan & Xiaowei Ding & Kay Giesecke, 2026. "Agentic Empirical Asset Pricing: Methodological Foundations," Papers 2609.00731, 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:2609.27051. 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.