Metraipolis › archive › dc_e0d687283f13

SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection — arXiv:2609.27287

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27287
License (as archived): CC0-1.0
Archived: 2026-10-08T10:13:32.075Z
SHA-256 of the archived text: 561db8f58066eed3eef3864cc3d6a5dbda7739766dbafcde379a9bd3cbd58d00
Stable URL of this page: https://metraipolis.com/documento/dc_e0d687283f13

How to cite

SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection — arXiv:2609.27287 — arXiv (en), https://arxiv.org/abs/2609.27287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e0d687283f13 (Metraipolis archive dc_e0d687283f13, sha256 561db8f58066eed3eef3864cc3d6a5dbda7739766dbafcde379a9bd3cbd58d00)

BibTeX

@misc{dce0d687283f13,
  title = {SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection — arXiv:2609.27287},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27287},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e0d687283f13; sha256 561db8f58066eed3eef3864cc3d6a5dbda7739766dbafcde379a9bd3cbd58d00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized burst attacks can cause losses before retraining. Production systems typically rely on tabular classifiers and rules, which can struggle to capture these emerging sequential patterns before periodic retraining occurs. We present SR-Fraud, an outcome-supervised reflective LLM framework that decouples request-time decisions from offline adaptation. A frozen, stateless agent scores each transaction from a Hybrid Episodic Window to track behavioral shifts, while an offline reflection agent proposes boundary hypotheses from matured errors. A deterministic verifier then admits only supported hypotheses into an executable knowledge state. On a production payment-fraud benchmark, SR-Fraud improves all detection metrics over its frozen decision agent, obtains higher point estimates than static and periodically retrained CatBoost, and detects an emerging fraud burst.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CR).
Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.27287 — 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 2026-10-08T09:26:35.731Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).