用自然语言对话完成银行核心业务，全球首个获监管批准的落地应用
Banking Done Right: Redefining Retail Banking with Language-Centric AI
- 四代理人协同处理指令，通过LoRA微调实现任务定制化
- 全内建模型与本地部署，确保合规与低延迟响应
- 监管认证支持核心交易，适合追求智能服务的金融机构
本文提出Ryt AI，一个基于大语言模型的原生智能体框架，驱动Ryt Bank实现客户通过自然语言对话完成核心金融操作。这是全球首个获监管机构批准的此类应用，突破以往助手仅限咨询或客服的局限。系统完全自研，采用内部开发的闭源大模型ILMU，通过四个由LLM驱动的代理（守卫、意图识别、支付、常见问题）协同工作，每个代理使用特定任务的LoRA适配器，并在银行内部基础设施中托管，实现高效一致的行为表现。通过确定性守则、人工确认机制和无状态审计架构，构建多层次安全与合规保障。结果表明，在严格治理下，自然语言接口可稳定支撑核心金融业务，真正实现‘正确地做银行业务’。
原文摘要 · Abstract (English)
This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank's infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance.
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。