Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Wei, Wang, Ting, Tian, Xinran, Lan, Wanshun, Feng, Xuhan, Li, Haoyue, Wang, Fangxin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.23580
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914420113801216
author Sun, Wei
Wang, Ting
Tian, Xinran
Lan, Wanshun
Feng, Xuhan
Li, Haoyue
Wang, Fangxin
author_facet Sun, Wei
Wang, Ting
Tian, Xinran
Lan, Wanshun
Feng, Xuhan
Li, Haoyue
Wang, Fangxin
contents Existing LLM-based Kubernetes diagnostic systems cannot learn from operational experience, operating on static knowledge bases without improving from past resolutions. We present MetaKube, an experience-aware LLM framework through three synergistic innovations: (1) an Episodic Pattern Memory Network (EPMN) that abstracts diagnostic patterns from historical resolutions and provides confidence-calibrated retrieval for both rapid pattern matching and guided causal exploration, (2) a meta-cognitive controller that dynamically routes between intuitive and analytical pathways based on problem familiarity, optimizing the trade-off between speed and depth, and (3) KubeLLM, a locally-deployable 8B model enhanced through domain-specific post-training on our 7,000-sample Kubernetes Fault Resolution Dataset. Evaluation on 1,873 real-world scenarios demonstrates MetaKube transforms Qwen3-8B from 50.9 to 90.5 points, approaching GPT-4.1 performance while ensuring complete data privacy. EPMN contributes 15.3% improvement through experiential learning, with continuous learning experiments showing progressive gains as the system accumulates operational knowledge. The source code and related resources are available at https://github.com/MetaKube-LLM-for-Kubernetes-Diagnosis/MetaKube.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23580
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
Sun, Wei
Wang, Ting
Tian, Xinran
Lan, Wanshun
Feng, Xuhan
Li, Haoyue
Wang, Fangxin
Machine Learning
Existing LLM-based Kubernetes diagnostic systems cannot learn from operational experience, operating on static knowledge bases without improving from past resolutions. We present MetaKube, an experience-aware LLM framework through three synergistic innovations: (1) an Episodic Pattern Memory Network (EPMN) that abstracts diagnostic patterns from historical resolutions and provides confidence-calibrated retrieval for both rapid pattern matching and guided causal exploration, (2) a meta-cognitive controller that dynamically routes between intuitive and analytical pathways based on problem familiarity, optimizing the trade-off between speed and depth, and (3) KubeLLM, a locally-deployable 8B model enhanced through domain-specific post-training on our 7,000-sample Kubernetes Fault Resolution Dataset. Evaluation on 1,873 real-world scenarios demonstrates MetaKube transforms Qwen3-8B from 50.9 to 90.5 points, approaching GPT-4.1 performance while ensuring complete data privacy. EPMN contributes 15.3% improvement through experiential learning, with continuous learning experiments showing progressive gains as the system accumulates operational knowledge. The source code and related resources are available at https://github.com/MetaKube-LLM-for-Kubernetes-Diagnosis/MetaKube.
title MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
topic Machine Learning
url https://arxiv.org/abs/2603.23580