发表机构
Ant International（蚂蚁国际）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对传统工业智能体模块化流水线的缺陷，提出OneModel范式，将业务逻辑与SOP内化至模型，在金融服务系统中实现延迟大幅降低、解决率提升，为工业智能体架构升级提供蓝图。
AI 中文摘要
传统工业智能体依赖模块化流水线，包含Router（路由模块）、Retriever（检索模块）、Planner（规划模块）、Executor（执行模块）、Responder（响应模块）、Reviewer（审核模块）及其他组件。这类系统常因大量临时补丁形成复杂迷宫，引发级联错误并导致高延迟。我们提出OneModel，一种从外部工作流向内化知识表示转变的可行范式。与将流动的用户意图拆分为静态步骤的模块化系统不同，OneModel将复杂业务逻辑和SOP（标准作业程序）直接整合到模型参数中。通过持续预训练（CPT）和逻辑编译SFT（监督微调），我们将碎片化的业务规则转化为统一注意力空间内的直观模型推理。OneModel部署于我们的全球金融服务系统中，有效打破了延迟、准确率与复杂度之间的权衡。在线A/B测试显示，端到端延迟降低超50%，从18.7秒降至8.0秒，同时智能解决率（IRR）从64.3%提升至83.3%。结果表明，OneModel可用内化的认知直觉替代脆弱的工程逻辑，为工业智能体从复杂、易出错的工作流向统一模型架构过渡提供了可扩展蓝图。
英文摘要
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.
CommentsAccepted to the ACL 2026 Industry Track (Oral). To appear in Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Industry Track)
