{"total":84,"rows":[{"id":"2311.04254","title":"Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation","created":"2023-11-07","cited_by_count":74,"area":"lr"},{"id":"2409.00899","title":"MarsCode Agent: AI-native Automated Bug Fixing","created":"2024-09-02","cited_by_count":71,"area":"agents"},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2310.16340","title":"RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models","created":"2023-10-25","cited_by_count":65,"area":"agents"},{"id":"2604.08618","title":"SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support","created":"2026-04-09","cited_by_count":48,"area":"agents"},{"id":"2501.06706","title":"AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds","created":"2025-01-12","cited_by_count":40,"area":"agents"},{"id":"2502.08224","title":"Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis","created":"2025-02-12","cited_by_count":34,"area":"agents"},{"id":"2401.13810","title":"Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2404.12135","title":"mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecture","created":"2024-04-18","cited_by_count":26,"area":"agents"},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25,"area":null},{"id":"2412.19823","title":"A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions","created":"2024-12-16","cited_by_count":25,"area":null},{"id":"2402.02820","title":"Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective","created":"2024-02-05","cited_by_count":24,"area":null},{"id":"2411.10213","title":"An Empirical Study on LLM-based Agents for Automated Bug Fixing","created":"2024-11-15","cited_by_count":23,"area":"agents"},{"id":"2404.03662","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","created":"2024-02-15","cited_by_count":19,"area":null},{"id":"2407.12165","title":"Building AI Agents for Autonomous Clouds: Challenges and Design Principles","created":"2024-07-16","cited_by_count":19,"area":"agents"},{"id":"2507.12472","title":"A Survey of AIOps in the Era of Large Language Models","created":"2025-06-23","cited_by_count":19,"area":null},{"id":"2404.00640","title":"Face It Yourselves: An LLM-Based Two-Stage Strategy to Localize Configuration Errors via Logs","created":"2024-03-31","cited_by_count":17,"area":null},{"id":"2410.09352","title":"LogLM: From Task-based to Instruction-based Automated Log Analysis","created":"2024-10-12","cited_by_count":15,"area":null},{"id":"2603.00468","title":"Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems","created":"2026-02-28","cited_by_count":15,"area":"agents"},{"id":"2504.20462","title":"TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systems","created":"2025-04-29","cited_by_count":13,"area":"agents"},{"id":"2508.20370","title":"Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thought","created":"2025-08-28","cited_by_count":13,"area":"lr"},{"id":"2408.00803","title":"A Comprehensive Survey on Root Cause Analysis in (Micro) Services: Methodologies, Challenges, and Trends","created":"2024-07-23","cited_by_count":10,"area":null},{"id":"2605.07161","title":"SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2406.05375","title":"LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis","created":"2024-06-08","cited_by_count":9,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2506.12270","title":"Cloud Infrastructure Management in the Age of AI Agents","created":"2025-06-13","cited_by_count":9,"area":"agents"},{"id":"2509.10858","title":"Large Language Models for Security Operations Centers: A Comprehensive Survey","created":"2025-09-13","cited_by_count":9,"area":null},{"id":"2601.02732","title":"Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices","created":"2026-01-06","cited_by_count":9,"area":"lr"},{"id":"2412.01377","title":"Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2507.22800","title":"The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach","created":"2025-07-30","cited_by_count":6,"area":"agents"},{"id":"2510.10074","title":"StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis","created":"2025-10-11","cited_by_count":5,"area":"agents"},{"id":"2403.06485","title":"Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approach","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2407.14402","title":"The Vision of Autonomic Computing: Can LLMs Make It a Reality?","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2501.11031","title":"AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model","created":"2025-01-19","cited_by_count":4,"area":null},{"id":"2502.09921","title":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","created":"2025-02-14","cited_by_count":4,"area":"inference"},{"id":"2506.02490","title":"Simplifying Root Cause Analysis in Kubernetes with StateGraph and LLM","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2601.21359","title":"Graph-Free Root Cause Analysis","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2604.11094","title":"E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2605.04530","title":"SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.08717","title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2408.01444","title":"No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Size","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2503.01475","title":"ProRCA: A Causal Python Package for Actionable Root Cause Analysis in Real-world Business Scenarios","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2605.04431","title":"Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2607.08010","title":"Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems","created":"2026-07-09","cited_by_count":3,"area":"agents"},{"id":"2402.17583","title":"FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systems","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2403.18639","title":"Dependency Aware Incident Linking in Large Cloud Systems","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2506.11635","title":"FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2512.22113","title":"PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2602.01317","title":"TxRay: Agentic Postmortem of Live Blockchain Attacks","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2603.21145","title":"NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuum","created":"2026-03-22","cited_by_count":2,"area":null},{"id":"2605.12729","title":"Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2410.10021","title":"Online Multi-modal Root Cause Identification in Microservice Systems","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2503.17783","title":"Energy-Aware LLMs: A step towards sustainable AI for downstream applications","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2510.21710","title":"A Feature Engineering Approach for Business Impact-Oriented Failure Detection in Distributed Instant Payment Systems","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2601.09258","title":"LatencyPrism: Online Non-intrusive Latency Sculpting for SLO-Guaranteed LLM Inference","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2603.03378","title":"AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.12218","title":"LLM-Enhanced Log Anomaly Detection: A Comprehensive Benchmark of Large Language Models for Automated System Diagnostics","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.23455","title":"CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend","created":"2026-04-25","cited_by_count":1,"area":"agents"},{"id":"2606.00582","title":"PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2607.11357","title":"OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis","created":"2026-07-13","cited_by_count":1,"area":"lr"},{"id":"2604.02382","title":"Interactive Clarification for Cloud Infrastructure-as-Code Synthesis","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.06171","title":"LLM-Augmented Knowledge Base Construction For Root Cause Analysis","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2605.02906","title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.22779","title":"FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection","created":"2026-05-21","cited_by_count":0,"area":"moe"},{"id":"2606.08590","title":"Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.13543","title":"NetCause: Counterfactual Learning for Root Cause Analysis in Large-Scale Networks","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.15943","title":"Graphical-Probabilistic Modeling of Generative Flows in LLM-Native Software Systems","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.13035","title":"FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2607.20005","title":"Safe Remediation as Risk-Constrained Intervention Decision in Microservice Systems","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.22385","title":"Agentic Root Cause Analysis through Evidence-Grounded Reasoning","created":"2026-07-24","cited_by_count":0,"area":"lr"},{"id":"2607.27290","title":"EvoCause: LLM-Guided Evolution of Causal Graphs for Root Cause Analysis","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.01955","title":"Agentic Self-Healing for Data and AI Pipelines: An Affordable Vendor-Agnostic Architecture using Open-Source Software","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.13120","title":"SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.21310","title":"Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.25661","title":"From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2608.26332","title":"Beyond Capability Benchmarks: Learning Operational Fingerprints of LLM Cloud Services from Production Incident Metadata","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28790","title":"ASTRA - Agentic System for Ticket Resolution and Analysis","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.00050","title":"Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.00227","title":"Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from LLM-Proposed Field Changes","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.33023","title":"SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36686","title":"Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14547","title":"A Self-Defining Operator for Distributed Applications","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.19222","title":"REPORT-OPS: Hybrid Evidence-Guided Reporting with Human-Supervised Refinement for HPC","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}