{"list":"other","total":77,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2403.02691","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","created":"2024-03-05","cited_by_count":538},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375},{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364},{"id":"2401.13178","title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","created":"2024-01-24","cited_by_count":339},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2402.07867","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-02-12","cited_by_count":267},{"id":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2503.00061","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","created":"2025-02-27","cited_by_count":125},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102},{"id":"2412.16682","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents","created":"2024-12-21","cited_by_count":99},{"id":"2305.15778","title":"Automatic Root Cause Analysis via Large Language Models for Cloud Incidents","created":"2023-05-25","cited_by_count":84},{"id":"2402.02338","title":"NetLLM: Adapting Large Language Models for Networking","created":"2024-02-04","cited_by_count":78},{"id":"2501.10868","title":"JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models","created":"2025-01-18","cited_by_count":71},{"id":"2008.06448","title":"Loghub: A Large Collection of System Log Datasets for AI-driven Log Analytics","created":"2020-08-14","cited_by_count":70},{"id":"1811.03509","title":"Tools and Benchmarks for Automated Log Parsing","created":"2018-11-08","cited_by_count":56},{"id":"2206.05871","title":"Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition","created":"2022-06-13","cited_by_count":56},{"id":"2502.05352","title":"ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks","created":"2025-02-07","cited_by_count":51},{"id":"2309.09298","title":"OWL: A Large Language Model for IT Operations","created":"2023-09-17","cited_by_count":43},{"id":"2411.00459","title":"Defense Against Prompt Injection Attack by Leveraging Attack Techniques","created":"2024-11-01","cited_by_count":40},{"id":"2407.01511","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","created":"2024-07-01","cited_by_count":39},{"id":"2301.03797","title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models","created":"2023-01-10","cited_by_count":38},{"id":"2505.06311","title":"Defending against Indirect Prompt Injection by Instruction Detection","created":"2025-05-08","cited_by_count":32},{"id":"2307.04945","title":"What do LLMs need to Synthesize Correct Router Configurations?","created":"2023-07-11","cited_by_count":29},{"id":"2502.18878","title":"Learning to Generate Structured Output with Schema Reinforcement Learning","created":"2025-02-26","cited_by_count":29},{"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},{"id":"2404.06411","title":"AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents","created":"2024-04-09","cited_by_count":28},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25},{"id":"2312.11988","title":"Xpert: Empowering Incident Management with Query Recommendations via Large Language Models","created":"2023-12-19","cited_by_count":22},{"id":"2509.07315","title":"SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs","created":"2025-09-09","cited_by_count":22},{"id":"2208.03938","title":"Constructing Large-Scale Real-World Benchmark Datasets for AIOps","created":"2022-08-08","cited_by_count":20},{"id":"2404.03662","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","created":"2024-02-15","cited_by_count":19},{"id":"2507.12472","title":"A Survey of AIOps in the Era of Large Language Models","created":"2025-06-23","cited_by_count":19},{"id":"2412.15540","title":"MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering","created":"2024-12-20","cited_by_count":17},{"id":"2406.06737","title":"Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications","created":"2024-06-10","cited_by_count":16},{"id":"2304.04661","title":"AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges","created":"2023-04-10","cited_by_count":15},{"id":"2504.07467","title":"Defense against Prompt Injection Attacks via Mixture of Encodings","created":"2025-04-10","cited_by_count":14},{"id":"2507.06323","title":"Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms","created":"2025-07-08","cited_by_count":7},{"id":"2510.01232","title":"Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks","created":"2025-09-23","cited_by_count":6},{"id":"1611.02537","title":"Network-wide Configuration Synthesis","created":"2016-11-08","cited_by_count":4},{"id":"1702.07375","title":"Delta-net: Real-time Network Verification Using Atoms","created":"2017-02-23","cited_by_count":4},{"id":"2008.11192","title":"Failures and Fixes: A Study of Software System Incident Response","created":"2020-08-25","cited_by_count":4},{"id":"2502.16395","title":"AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science","created":"2025-02-23","cited_by_count":4},{"id":"2412.01066","title":"Practitioners' Expectations on Log Anomaly Detection","created":"2024-12-02","cited_by_count":3},{"id":"2509.23516","title":"Network-Optimised Spiking Neural Network for Event-Driven Networking","created":"2025-09-27","cited_by_count":3},{"id":"2510.03705","title":"Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods","created":"2025-10-04","cited_by_count":3},{"id":"1905.04648","title":"Automating chaos experiments in production","created":"2019-05-12","cited_by_count":2},{"id":"2209.12870","title":"Test Coverage for Network Configurations","created":"2022-09-26","cited_by_count":2},{"id":"2508.06394","title":"When AIOps Become \"AI Oops\": Subverting LLM-driven IT Operations via Telemetry Manipulation","created":"2025-08-08","cited_by_count":2},{"id":"2510.11291","title":"Network-Optimised Spiking Neural Network (NOS) Scheduling for 6G O-RAN: Spectral Margin and Delay-Tail Control","created":"2025-10-13","cited_by_count":2},{"id":"2510.14503","title":"Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals","created":"2025-10-16","cited_by_count":2},{"id":"2402.09538","title":"Learning From Lessons Learned: Preliminary Findings From a Study of Learning From Failure","created":"2024-02-14","cited_by_count":1},{"id":"2408.15516","title":"Predicting Parameter Change's Effect on Cellular Network Time Series","created":"2024-08-28","cited_by_count":1},{"id":"2507.22711","title":"OFCnetLLM: Large Language Model for Network Monitoring and Alertness","created":"2025-07-30","cited_by_count":1},{"id":"2601.00389","title":"NOS-Gate: Queue-Aware Streaming IDS for Consumer Gateways under Timing-Controlled Evasion","created":"2026-01-01","cited_by_count":1}],"next_cursor":null}