用大模型驱动的智能体框架提升欺诈检测精度与可解释性。
SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection
- 构建三智能体协同系统，基于六层数据诊断树与自然语言反馈优化决策。
- 在五数据集上平均提升F1 40.86%，胜出96%的对比实验。
- 适合需高精度、可解释的金融与电商业务场景使用。
支付、电商及电信系统中的欺诈检测需具备个体级精准度、严重类别不平衡下的鲁棒性，以及风险管理人员易于理解的特点。现有方法至少在一项要求上存在不足：自动化机器学习系统在固定数值空间中搜索，缺乏对数据语义的理解；图神经网络方法依赖预定义关系图，在个体决策层面仍不透明；通用大语言模型代理的设计未考虑实际欺诈检测中召回率与精确率的约束。本文提出SAGE，首个端到端的、由大模型驱动的多智能体欺诈检测框架。SAGE协调三个专用智能体，基于六层数据诊断树（DDT）和由自然语言梯度引导的马尔可夫决策过程，自动在欺诈特异性奖励下优化模型。在五个欺诈数据集与五个LLM骨干模型上，SAGE在96.00%的方法-数据集比较中胜出，平均F1提升40.86%。代码已公开于https://github.com/yichenC1c/SAGE。
原文摘要 · Abstract (English)
Fraud detection in payment, e-commerce, and telecommunications systems requires accuracy at the individual level, robustness under severe class imbalance, and ease of understanding for risk managers. Existing methods fall at least one of these requirements: automated machine learning systems search a fixed numerical space without semantic awareness of the dataset; graph neural network-based methods require pre-defined relational graphs and remain opaque at the individual-decision level; and the design of general-purpose large language model (LLM) agents does not consider the recall and precision constraints specific to real-world fraud detection. In this paper, we propose SAGE, the first end-to-end LLM-driven multi-agent framework for fraud detection. SAGE coordinates three dedicated agents that make decisions based on a six-layer Data Diagnostic Tree (DDT) and a Markov decision process guided by natural-language gradients, automatically optimizing the model under a fraud-specific reward. On five fraud datasets and five LLM backbones, SAGE wins $96.00\%$ of method--dataset comparisons and improves F1 by an average of $40.86\%$ over baselines. The code is available at https://github.com/yichenC1c/SAGE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。