---
title: "PersonaAgent: Retrieval-Augmented Transaction Anomaly Scoring with Refreshable Multi-Entity Persona Memory"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08094v1"
permalink: "https://feed.astralor.com/items/itm_b28feee81fa0bba35d6d4ae6"
published: "2026-11-05T14:37:16.000Z"
score: 58
channel: "tech"
tags: ["AI Agent","推理效率","RAG","PersonaAgent","Retrieval-Augmented Transaction Anomaly","Scoring","Refreshable Multi-Entity Persona","Memory"]
---

# PersonaAgent: Retrieval-Augmented Transaction Anomaly Scoring with Refreshable Multi-Entity Persona Memory

## 速览

In large-scale payment networks, entities (card, merchant, etc.) and their interactions play a key role in transaction anomaly detection. However, transaction patterns between different entities usually change more freq…

## 关键点

- In large-scale payment networks, entities (card, merchant, etc.) and their interactions play a key role in transaction anomaly detection.
- However, transaction patterns between different entities usually change more frequently than the production model refresh schedule.
- Meanwhile, entity embedding tables suffer from high-cardinality and sparse interaction issues.

## 全文

In large-scale payment networks, entities (card, merchant, etc.) and their interactions play a key role in transaction anomaly detection. However, transaction patterns between different entities usually change more frequently than the production model refresh schedule. Meanwhile, entity embedding tables suffer from high-cardinality and sparse interaction issues. To resolve the above challenges, we present PersonaAgent, an agentic transaction anomaly detection framework which represents the latest entity behavior signals as personas and saves them in a refreshable memory. Offline, a weekly scheduled batch job is used to extract the latest behavior signals and update them in the memory. At inference time, a lightweight adapter retrieves the corresponding entity behavior signals of each transaction from memory and uses them to augment the base anomaly classifier's scoring. Through comprehensive benchmarking with different anomaly detection models at Visa, PersonaAgent is able to score transactions efficiently (a 1,000-transaction CPU batch in 1-2 ms), lifting the PR-AUC by 0.65-6.58% and the production business metric by 8.93-14.24% relatively in deployment.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_b28feee81fa0bba35d6d4ae6