AI PB主动生成合规个性投资建议，落地真实零售金融场景。
AI PB: A Grounded Generative Agent for Personalized Investment Insights
- 分组件调度层按数据敏感度自动切换内外部大模型
- 混合检索融合OpenSearch与金融嵌入模型，精准获取信息
- 多阶段推荐融合规则、行为建模与上下文强化学习
我们提出AI PB，一个在真实零售金融中部署的生产级生成型智能体。与被动响应的聊天机器人不同，AI PB能主动生成基于证据、符合监管且个性化的投资建议。系统包含三部分：(i) 基于数据敏感度确定性路由内外部大模型的组件化编排层；(ii) 结合OpenSearch与金融领域嵌入模型的混合检索管道；(iii) 融合规则启发式、序列行为建模和上下文老虎机的多阶段推荐机制。系统在韩国金融监管要求下全本地化运行，使用Docker Swarm与vLLM，部署于24块NVIDIA H100 GPU上。通过人工评估与系统指标验证，显式路由与分层安全机制可实现高风险金融场景下的可信生成。
原文摘要 · Abstract (English)
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.
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。