MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis

TL;DR

MetaKube is an experience-aware LLM framework for Kubernetes failure diagnosis that learns from operational history, improving diagnostic accuracy and efficiency while maintaining data privacy.

Contribution

It introduces EPMN, a meta-cognitive controller, and domain-specific fine-tuning of KubeLLM, enabling experiential learning and improved diagnosis performance.

Findings

MetaKube improves diagnosis accuracy from 50.9 to 90.5 points.

EPMN contributes a 15.3% improvement through experiential learning.

MetaKube approaches GPT-4.1 performance while ensuring data privacy.

Abstract

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.