Metraipolis › archive › dc_8fa0b2d31cc5

Hard to Fool: A Bounded LLM Research Loop for Quantitative Finance, and What Two Dozen Campaigns Found — arXiv:2611.06607

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06607
License (as archived)
CC0-1.0
Archived
2026-11-05T18:35:55.471Z
SHA-256 of the archived text
6166b12d3c835351d7e524211ae581f32fdfa090efb6b7d45573b36ee8c4ebf3
Stable URL of this page
https://metraipolis.com/documento/dc_8fa0b2d31cc5

How to cite

Hard to Fool: A Bounded LLM Research Loop for Quantitative Finance, and What Two Dozen Campaigns Found — arXiv:2611.06607 — arXiv (en), https://arxiv.org/abs/2611.06607 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8fa0b2d31cc5 (Metraipolis archive dc_8fa0b2d31cc5, sha256 6166b12d3c835351d7e524211ae581f32fdfa090efb6b7d45573b36ee8c4ebf3)
BibTeX
@misc{dc8fa0b2d31cc5,
  title = {Hard to Fool: A Bounded LLM Research Loop for Quantitative Finance, and What Two Dozen Campaigns Found — arXiv:2611.06607},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06607},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8fa0b2d31cc5; sha256 6166b12d3c835351d7e524211ae581f32fdfa090efb6b7d45573b36ee8c4ebf3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06607. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic research loops that let a language model propose a change, run a fixed experiment and keep whatever improves the metric work well in machine learning. In trading research the same loop is a machine for producing false discoveries: a backtest that "improves the metric" is, by default, overfit, look-ahead, a multiple-comparisons artifact, cost-free, or market drift wearing a strategy. We describe Autonomous Quant Researcher, an open-source loop built on the opposite premise: the model proposes, and only trusted code decides. Proposals are strict declarative JSON over a fixed vocabulary, so there is no model-written code to sandbox. Evaluation runs on immutable chronological stores split into discovery, validation and a final holdout that can be opened exactly once, after a durable receipt is written. Acceptance is a conjunction of absolute gates (positive edge and net P&L after costs, a positive weekly-cluster bootstrap lower bound, survival at elevated costs, per-year stability and sample floors), never a single score. Duplicates are refused before they spend a trial, and every formulation, refusal, crash and result is kept in a hash-chained, append-only ledger. We report every campaign run to date, across 0DTE options priced from traded option bars, overnight SPX verticals, daily ETF rules, technical-analysis premises, Kalshi crypto binaries, earnings options, off-exchange volume and a pre-registered alternative-data campaign. Most hypotheses fail, and we report them. Two results survive their pre-registered bars. The clearest example of the loop working is a failure: a language-model survivor that passed discovery and validation with Sharpe ratios near 3 and fell to 0.26 on its single holdout use. The value of such a loop lies less in what it finds than in how hard it is to make it report something that is not there.

Tema degli esploratori: economia dei servizi IA (elenco arXiv q-fin.CP, nuovi lavori del giorno).
Categorie arXiv: Computational Finance (q-fin.CP) ; Trading and Market Microstructure (q-fin.TR).
Pagina del lavoro: https://arxiv.org/abs/2611.06607 — 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 2026-11-05T18:31:01.566Z dalla pagina https://arxiv.org/list/q-fin.CP/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).