mlsanityData to 14 Oct 2026

Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models

arXiv 2501.14170 ↗First posted 24 Jan 2025cs.LG cs.DC cs.MAcited by 19

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Observability in cloud infrastructure is critical for service providers, driving the widespread adoption of anomaly detection systems for monitoring metrics. However, existing systems often struggle to simultaneously achieve explainability, reproducibility, and autonomy, which are three indispensable properties for production use. We introduce Argos, an agentic system for detecting time-series anomalies in cloud infrastructure by leveraging large language models (LLMs). Argos proposes to use explainable and reproducible anomaly rules as intermediate representation and employs LLMs to autonomously generate such rules. The system will efficiently train error-free and accuracy-guaranteed anomaly rules through multiple collaborative agents and deploy the trained rules for low-cost online anomaly detection. Through evaluation results, we demonstrate that Argos outperforms state-of-the-art methods, increasing F1 scores by up to 9.5% and 28.3% on public anomaly detection datasets and an internal dataset collected from Microsoft, respectively.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 75 references that are in the map. First posted on arXiv 24 Jan 2025.

Builds on

21 of 75 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2024GPT-4o System Cardcited by 4,588
  7. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  8. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  9. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  10. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  11. 2021Investigating the Limitations of Transformers with Simple Arithmetic Taskscited by 139
  12. 2024The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinismcited by 116
9 more
  1. 2024Large language models can be zero-shot anomaly detectors for time series?cited by 31
  2. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 29
  3. 2024TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Modelscited by 23
  4. 2024Can LLMs Serve As Time Series Anomaly Detectors?cited by 22
  5. 2022Constructing Large-Scale Real-World Benchmark Datasets for AIOpscited by 20
  6. 2024A Survey of AIOps for Failure Management in the Era of Large Language Modelscited by 16
  7. 2023AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challengescited by 15
  8. 2024Cloud Atlas: Efficient Fault Localization for Cloud Systems using Language Models and Causal Insightcited by 12
  9. 2024AIOps Solutions for Incident Management: Technical Guidelines and A Comprehensive Literature Reviewcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 11.

19 papers.

Sort:

By area:

  1. 2025KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflowscited by 56
  2. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  3. 2025AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detectioncited by 8
  4. 2025Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehousecited by 6
  5. 2026AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoningcited by 5
  6. 2025Fortifying the Agentic Web: A Unified Zero-Trust Architecture Against Logic-layer Threatscited by 3
  7. 2026LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detectioncited by 2
  8. 2026Visual Reasoning over Time Series via Multi-Agent Systemcited by 2
  9. 2026From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligencecited by 2
  10. 2026LLM Agents for Time-Series: A Surveycited by 1
  11. 2025From Time Series Analysis to Question Answering: A Survey in the LLM Eracited by 0
  12. 2025Exploring LLM-based Frameworks for Fault Diagnosiscited by 0
7 more
  1. 2025Physics-Informed Large Language Models for HVAC Anomaly Detection with Autonomous Rule Generationcited by 0
  2. 2026Multi-Agent Collaborative Intrusion Detection for Low-Altitude Economy IoT: An LLM-Enhanced Agentic AI Frameworkcited by 0
  3. 2026Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triagecited by 0
  4. 2026Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detectioncited by 0
  5. 2026Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Modelscited by 0
  6. 2026Memory in Deep Time-Series Modelscited by 0
  7. 2026Agentic RCA for Internet-Scale Services Using Constrained Creativitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Generalizable Context-aware Anomaly Detection: A Large-scale Benchmark in Cloud Environments
  2. 2026Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
  3. 2026AgenticTwin: An Agentic LLM Framework Integrated with Digital Twin for Anomaly Detection
  4. 2026AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
  5. 2025CodeAD: Synthesize Code of Rules for Log-based Anomaly Detection with LLMs
  6. 2023RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
  7. 2026ARuleCon: Agentic Security Rule Conversion
  8. 2025AnomalyGen: An Automated Semantic Log Sequence Generation Framework with LLM for Anomaly Detection