AI PB: A Grounded Generative Agent for Personalized Investment Insights

📝 Original Info

• Title: AI PB: A Grounded Generative Agent for Personalized Investment Insights
• ArXiv ID: 2510.20099
• Date: 2025-10-23
• Authors: ** 정보가 제공되지 않았습니다. (논문에 명시된 저자 정보를 입력해 주세요.) **

📝 Abstract

We present AI PB, a production-scale generative agent deployed in real retail finance. Unlike reactive chatbots that answer queries passively, AI PB proactively generates grounded, compliant, and user-specific investment insights. It integrates (i) a component-based orchestration layer that deterministically routes between internal and external LLMs based on data sensitivity, (ii) a hybrid retrieval pipeline using OpenSearch and the finance-domain embedding model, and (iii) a multi-stage recommendation mechanism combining rule heuristics, sequential behavioral modeling, and contextual bandits. Operating fully on-premises under Korean financial regulations, the system employs Docker Swarm and vLLM across 24 X NVIDIA H100 GPUs. Through human QA and system metrics, we demonstrate that grounded generation with explicit routing and layered safety can deliver trustworthy AI insights in high-stakes finance.

💡 Deep Analysis

📄 Full Content

Reference