发表机构
TEG, Tencent Inc.; Wuhan University（腾讯公司TEG; 武汉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
腾讯提出SiriusDeliver端到端交付自动化智能体，集成三类组件，经离线实验和腾讯云WeData大规模部署验证，可显著提升DW交付的成功率、效率，缩短交付时间与工程师工作量。
AI 中文摘要
企业数据仓库（DW）支撑着业务关键型分析工作，但仓库任务交付仍是一个复杂的生产流程，涉及上下文检索、工作流配置、代码生成、平台提交及故障诊断。尽管大语言模型（LLM）和编码智能体已推动软件开发进步，但它们不足以胜任生产级DW交付，后者需要感知依赖的编排、感知生命周期的制品控制，以及对不断演进的平台实践的持续适配。我们提出SiriusDeliver，这是一款面向生产级仓库任务提交的端到端交付自动化智能体。SiriusDeliver集成了三个组件：编排仓库技能的分层交付智能体、在平台执行前后验证和修订制品的制品生命周期控制模块，以及从交付轨迹中维护可复用技能的轨迹驱动型技能演化机制。我们通过离线数据集和腾讯云WeData上的大规模生产部署对SiriusDeliver进行评估。针对真实仓库交付案例的离线实验显示，SiriusDeliver相比代表性基线提升了交付成功率和自动化效率。在覆盖6个业务团队、4类仓库任务的两个月部署期间，SiriusDeliver服务了3600名月活跃用户，支撑了18240次交付会话，实现了87.2%的端到端成功率和73.5%的自主提交率。一项为期一个月的A/B测试显示，SiriusDeliver将交付中位时间从228分钟缩短至23分钟，工程师工作量从95分钟减少至11分钟，同时保持了相当的最终交付成功率。
英文摘要
Enterprise data warehouses (DWs) support business-critical analytics, but warehouse task delivery remains a complicated production process involving context retrieval, workflow configuration, code generation, platform submission, and failure diagnosis. Although large language models (LLMs) and coding agents have improved software development, they are insufficient for production DW delivery, which requires dependency-aware orchestration, lifecycle-aware artifact control, and continuous adaptation to evolving platform practices. We present SiriusDeliver, an end-to-end delivery automation agent for production warehouse task submission. SiriusDeliver integrates three components: a hierarchical delivery agent that orchestrates warehouse skills, an artifact lifecycle control module that verifies and revises artifacts before and after platform execution, and a trace-driven skill evolution mechanism that maintains reusable skills from delivery trajectories. We evaluate SiriusDeliver through offline datasets and large-scale production deployment on Tencent Cloud WeData. Offline experiments on real-world warehouse delivery cases show that SiriusDeliver improves delivery success and automation efficiency over representative baselines. During a two-month deployment across 6 business teams and 4 warehouse task types, SiriusDeliver served 3,600 monthly active users and supported 18,240 delivery sessions, achieving an 87.2% end-to-end success rate and a 73.5% autonomous submission rate. A one-month A/B test shows that SiriusDeliver reduces median delivery time from 228 to 23 minutes and engineer effort from 95 to 11 minutes, while maintaining comparable final delivery success.
Comments13 pages, 13 figures, 3 tables. Under submission
