arXiv：cs.AI· Shihang Li, Thomas Anderson, Ratul Mahajan, Simon Peter, Luke Zettlemoyer·· 17 小时前
自学习运维智能体 SDO：用 playbooks 与 detectors 让分布式应用故障处理随时间改进
A Self-Defining Operator for Distributed Applications
AI 导读
针对 LLM 运维智能体每次排查都从零开始的问题，研究者提出自学习运维智能体 SDO，它会把已解决的事故蒸馏为可复用的诊断 playbooks 和检测脚本 detectors，平时持续运行 detectors，仅在触发时才调用 LLM，token 成本随事故数量而非运维时长增长。在 11 个开源微服务应用上，SDO 将复发故障的解决时间缩短 52%，并已开源。
正文
Abstract:To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but unlike experienced human operators they do not improve as they handle more incidents. Each investigation starts from scratch, re-deriving likely causes and re-testing hypotheses even when a similar fault was resolved in the past. We present a self-defining operator (SDO) that improves with time by updating its operational behavior and memory. When SDO resolves an incident, it distills that experience into playbooks, which describe reusable diagnostic instructions for future incidents with similar faults, and detectors, scripts that take application telemetry as input and output relevant playbook(s). SDO continuously runs the detectors and invokes LLMs only when one fires, so its token cost scales with incident count rather than with operational time. Across 11 open-source microservice applications, SDO cuts resolution time by 52% on recurring faults while keeping per-incident cost low. SDO is open source at this https URL.
| Subjects: | Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14547 [cs.DC] |
| (or arXiv:2610.14547v2 [cs.DC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14547 arXiv-issued DOI via DataCite |
Submission history
From: Shihang Li [view email]
[v1]
Sat, 10 Oct 2026 04:08:13 UTC (2,590 KB)
[v2]
Wed, 14 Oct 2026 06:00:51 UTC (2,590 KB)
来源：arXiv：cs.AI · arxiv.org