SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection

2026-06-06 · Yichen Chen, Siying Li, Yuhang Liang, Lijun Wang, Renyang Liu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.08146

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural Network Fraud Detection

Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping

2026-06-30 · Tao Chen, Lizheng Liu, Jiaxu Wang, Ziyue Jiang 외 arxiv

Generalizable robotic grasping in cluttered environments is essential for deploying manipulators in unstructured human spaces, yet existing VLM-based methods rely on visual similarity for object matching, neglecting phys…

Spatial Reasoning Robotic Grasping

OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM Agent

2025-07-03 · Bowen Chen, Zhao Wang, Shingo Takamatsu arxiv

Keyword decision in Sponsored Search Advertising is critical to the success of ad campaigns. While LLM-based methods offer automated keyword generation, they face three major limitations: reliance on large-scale query-ke…

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

2026-07-30 · Binbin Zheng, Zijun Xie, Guanqun Zhao, Enlei Gong 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recur…

Reinforcement Learning

GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection

2025-08-23 · Melissa Kazemi Rad, Alberto Purpura, Himanshu Kumar, Emily Chen 외 arxiv

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Langu…

Synthetic Data Generation Text Classification Data Augmentation

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

2025-09-24 · Yandan Yang, Baoxiong Jia, Shujie Zhang, Siyuan Huang arxiv

Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While rec…

Indoor Scene Synthesis Scene Generation