Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.03512 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914462622023680 |
|---|---|
| author | Lin, Zhenfeng Hu, Haoji Hao, Ming Zhang, Xuchao Zhang, Ryan Li, Junhao Li, Ze Kulygin, Oleg Bansal, Chetan Tuna, Hatay Chintalapati, Murali Jiang, Sheila Zafar, Salman Anderson, Angie |
| author_facet | Lin, Zhenfeng Hu, Haoji Hao, Ming Zhang, Xuchao Zhang, Ryan Li, Junhao Li, Ze Kulygin, Oleg Bansal, Chetan Tuna, Hatay Chintalapati, Murali Jiang, Sheila Zafar, Salman Anderson, Angie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03512 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ActionNex: A Virtual Outage Manager for Cloud Computing Lin, Zhenfeng Hu, Haoji Hao, Ming Zhang, Xuchao Zhang, Ryan Li, Junhao Li, Ze Kulygin, Oleg Bansal, Chetan Tuna, Hatay Chintalapati, Murali Jiang, Sheila Zafar, Salman Anderson, Angie Artificial Intelligence 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. |
| title | ActionNex: A Virtual Outage Manager for Cloud Computing |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.03512 |