arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.03512cs.AI
收藏

ActionNex:云计算中的虚拟故障管理器

ActionNex: A Virtual Outage Manager for Cloud Computing

Microsoft PRIMO(微软PRIMO);Microsoft Research(微软研究院);Microsoft Azure Core(微软Azure Core)
Zhenfeng Lin, Haoji Hu, Ming Hao, Xuchao Zhang, Ryan Zhang, Junhao Li, Ze Li, Oleg Kulygin, Chetan Bansal, Hatay Tuna, Murali Chintalapati, Sheila Jiang, Salman… 展开作者

Zhenfeng Lin, Haoji Hu, Ming Hao, Xuchao Zhang, Ryan Zhang, Junhao Li, Ze Li, Oleg Kulygin, Chetan Bansal, Hatay Tuna, Murali Chintalapati, Sheila Jiang, Salman Zafar, Angie Anderson

AI总结:

本文提出ActionNex,一个生产级智能系统,通过多模态信号处理和分层记忆子系统,实现故障管理的端到端支持,包括实时更新、知识蒸馏和基于角色和阶段的最优行动推荐,实验表明其在真实Azure故障中达到71.4%的精度和52.8-54.8%的召回率。

摘要:

大规模云操作中的故障管理仍然高度依赖人工,需要快速分诊、跨团队协调和经验驱动决策,在部分可观测条件下。我们提出了ActionNex,一个生产级代理系统,支持端到端故障协助,包括实时更新、知识蒸馏和基于角色和阶段的最优行动推荐。ActionNex接收多模态操作信号(如故障内容、遥测和人类通信),并将它们压缩成关键事件,代表有意义的状态转换。它将感知层与分层记忆子系统结合:长期的关键-条件-行动(KCA)知识从流程手册和历史执行中蒸馏出来,事件性记忆的先前故障,以及工作记忆的实时上下文。推理代理将当前关键事件与预条件对齐,检索相关记忆并生成可操作的推荐;执行的人类行动作为隐含反馈信号,使系统在人类-代理混合系统中持续自我进化。我们使用两个互补的真实Azure故障集(8M tokens,4000个关键事件)评估ActionNex,达到71.4%的精度和52.8-54.8%的召回率。该系统已在生产环境中试点,并获得了积极的早期反馈。

英文摘要:

Outage management in large-scale cloud operations remains heavily manual, requiring rapid triage, cross-team coordination, and experience-driven decisions under partial observability. We present \textbf{ActionNex}, a production-grade agentic system that supports end-to-end outage assistance, including real-time updates, knowledge distillation, and role- and stage-conditioned next-best action recommendations. ActionNex ingests multimodal operational signals (e.g., outage content, telemetry, and human communications) and compresses them into critical events that represent meaningful state transitions. It couples this perception layer with a hierarchical memory subsystem: long-term Key-Condition-Action (KCA) knowledge distilled from playbooks and historical executions, episodic memory of prior outages, and working memory of the live context. A reasoning agent aligns current critical events to preconditions, retrieves relevant memories, and generates actionable recommendations; executed human actions serve as an implicit feedback signal to enable continual self-evolution in a human-agent hybrid system. We evaluate ActionNex on eight real Azure outages (8M tokens, 4,000 critical events) using two complementary ground-truth action sets, achieving 71.4\% precision and 52.8-54.8\% recall. The system has been piloted in production and has received positive early feedback.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑