LLM4Ops

Content

Survey

24_A Survey of AIOps for Failure Management in the Era of Large Language Models [paper]

24_SC_Large Language Models for Anomaly Detection in Computational Workflows: From Supervised Fine-Tuning to In-Context Learning [paper]
24_Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts [paper] [code]
24_Large language models can be zero-shot anomaly detectors for time series? [paper]
24_RAGLog: Log Anomaly Detection using Retrieval Augmented Generation [paper]

24_NSDI_NetAssistant: Dialogue Based Network Diagnosis in Data Center Networks [paper]
24_mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecture [paper]
24_ICSE_Xpert: Empowering Incident Management with Query Recommendations via Large Language Models [paper]
24_Sigops_LLexus: an AI agent system for incident management [paper]
24_CIKM_RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models [paper]
24_FSE Companion_Leveraging Large Language Models for the Auto-remediation of Microservice Applications: An Experimental Study [paper]
24_FSE Companion_MonitorAssistant: Simplifying Cloud Service Monitoring via Large Language Models [paper]
24_ICSE_LogExpert: Log-based Recommended Resolutions Generation using Large Language Model [paper]
24_Eurosys_Empowering Practical Root Cause Analysis by Large Language Models for Cloud Incidents [paper]
23_D-Bot: Database Diagnosis System using Large Language Models [paper] [code]
23_FSE_Assess and Summarize: Improve Outage Understanding with Large Language Models [paper]
23_ICSE_Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models [paper]
23_LLM As DBA [paper]

24_LLMTune: Accelerate Database Knob Tuning with Large Language Models [paper]
24_VLDB_GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization [paper]
24_Configuration Validation with Large Language Models [paper]
24_GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation [paper]
24_Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents [paper]
24_ICSE-SEIP_MissConf: LLM-Enhanced Reproduction of Configuration-Triggered Bugs [paper]
24_ISSTA_Config_Face It Yourselves: An LLM-Based Two-Stage Strategy to Localize Configuration Errors via Logs [paper]