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

arXiv: https://arxiv.org/abs/2609.27287 · HTML: https://mlsanity.com/paper/2609.27287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [FinBERT: A Pretrained Language Model for Financial Communications](https://mlsanity.com/paper/2006.08097/) (2020)
- [SCARFF: a Scalable Framework for Streaming Credit Card Fraud Detection with Spark](https://mlsanity.com/paper/1709.08920/) (2017)
- [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://mlsanity.com/paper/2507.17131/) (2025)
- [TitAnt: Online Real-time Transaction Fraud Detection in Ant Financial](https://mlsanity.com/paper/1906.07407/) (2019)
- [UniPredict: Large Language Models are Universal Tabular Classifiers](https://mlsanity.com/paper/2310.03266/) (2023)
- [Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection](https://mlsanity.com/paper/2512.13040/) (2025)
- [LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection](https://mlsanity.com/paper/2509.18719/) (2025)
- [TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation](https://mlsanity.com/paper/2606.08295/) (2026)

## Abstract (arXiv)

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.