MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
Wei Sun, Ting Wang, Xinran Tian, Wanshun Lan, Xuhan Feng, Haoyue Li, Fangxin Wang
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Improving Language Models by Retrieving from Trillions of Tokens cites Retrieval Augmented Language Model Pre-Training
- ReAct: Synergizing Reasoning and Acting in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on5
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
- Improving Language Models by Retrieving from Trillions of TokensSebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai et al.ICML 2022 · 1,629 citations
- An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance IdentificationRuike Zhang, Yuan Tian, Penghui Wei, Daniel Zeng et al.EMNLP Findings 2024 · 6 citations
- ReAct: Synergizing Reasoning and Acting in Language ModelsShunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du et al.ICLR 2023
Related papers
- MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal KnowledgeShuai Liang, Pengfei Chen, Bozhe Tian, Gou Tan et al.FSE 2026 · 4 citations
- MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic OptimizationHaidong Xin, Xinze Li, Zhenghao Liu, Yukun Yan et al.ACL Findings 2026
- Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM ReasoningZiqing Zhuang, Linhai Zhang, Jiasheng Si, Deyu Zhou et al.ACL 2026
- MetaReflection: Learning Instructions for Language Agents using Past ReflectionsPriyanshu Gupta, Shashank Kirtania, Ananya Singha, Sumit Gulwani et al.EMNLP 2024 · 1 citation
- Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem SolvingAniket Didolkar, Anirudh Goyal, Nan Rosemary Ke, Siyuan Guo et al.NeurIPS 2024 · 101 citations
