Metraipolis › archive › dc_bf12fdb016f4

Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors — arXiv:2609.27051

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27051
License (as archived)
CC0-1.0
Archived
2026-10-08T09:11:05.083Z
SHA-256 of the archived text
4c96b42004ed4c1e5845a8e79ff0477bb7cdfb55d6f10e9881089c0375dbd420
Stable URL of this page
https://metraipolis.com/documento/dc_bf12fdb016f4

How to cite

Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors — arXiv:2609.27051 — arXiv (en), https://arxiv.org/abs/2609.27051 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf12fdb016f4 (Metraipolis archive dc_bf12fdb016f4, sha256 4c96b42004ed4c1e5845a8e79ff0477bb7cdfb55d6f10e9881089c0375dbd420)
BibTeX
@misc{dcbf12fdb016f4,
  title = {Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors — arXiv:2609.27051},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27051},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf12fdb016f4; sha256 4c96b42004ed4c1e5845a8e79ff0477bb7cdfb55d6f10e9881089c0375dbd420},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27051. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Portfolio Management (q-fin.PM); Statistical Finance (q-fin.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.27051 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T08:13:26.468Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).