把复杂业务流程内化到模型里，让智能客服更准更快。
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
- 将业务规则直接编入模型参数，取代传统分步流程
- 线上测试显示延迟降50%以上，解决率从64.3%升至83.3%
- 适合需要高可靠、低延迟的企业级智能系统
传统工业级智能体依赖路由、检索、规划、执行等模块化流程，常因碎片化导致错误蔓延和高延迟。本文提出OneModel，将复杂业务逻辑与SOP直接内化到模型参数中，通过持续预训练（CPT）与逻辑编译微调（SFT），在统一注意力空间中实现模型自主推理。部署于全球金融服务平台后，端到端延迟由18.7秒降至8.0秒（降幅超50%），智能解决率（IRR）从64.3%提升至83.3%。结果表明，该方法可替代脆弱的工程逻辑，以认知直觉实现可扩展的统一架构。
原文摘要 · Abstract (English)
Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency. We propose OneModel, an applicable paradigm shift from external workflows to internalized knowledge representation. Unlike modular systems that slice fluid user intents into static steps, OneModel consolidates complex business logic and SOPs directly into the model parameters. Through Continual Pre-training (CPT) and logic-compilation SFT, we transform fragmented business rules into intuitive model reasoning within a unified attention space. Deployed in our global financial service system, OneModel effectively breaks the trade-off between latency, accuracy, and complexity. Online A/B testing demonstrates an end-to-end latency reduction of more than 50 percent, from 18.7 seconds to 8.0 seconds, while the Intelligent Resolution Rate (IRR) increases from 64.3 percent to 83.3 percent. The results show that OneModel can replace brittle engineering logic with internalized cognitive intuition, offering a scalable blueprint for transitioning industrial agents from complex, error-prone workflows to unified model architectures.
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。