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

2026-09-22

AI Summary

为解决实时支付欺诈检测中的非平稳性问题，提出SR-Fraud框架，通过冻结代理和离线反思代理结合的方法来捕捉行为变化并提高检测性能。

Abstract

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.

Problem

• real-time payment fraud detection
• non-stationary streaming prediction
• adversaries adapt
• localized burst attacks
• tabular classifiers

Innovation

• outcome-supervised
• reflective LLM
• Hybrid Episodic Window
• offline reflection agent
• deterministic verifier