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

Source: [MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis](<https://www.sota2.com/research/paper/69c4bd650636e5bf4afc7444>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T05:00:04.194Z

Authors: Wei Sun, Ting Wang, Xinran Tian, Wanshun Lan, Xuhan Feng, Haoyue Li, Fangxin Wang

Published: 2026-03-24T14:21:01.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Kubernetes failure diagnosis on KubeFault 1.0 (test)](<https://www.sota2.com/research/sota/kubernetes-failure-diagnosis-on-kubefault-1-0-test.md>): Kubernetes failure diagnosis; KubeFault 1.0 (test); Effectiveness: 91.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.23580>)

[PDF](<https://arxiv.org/pdf/2603.23580.pdf>)
