Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| 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 |