# CALM: A Framework for Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streams

arXiv: https://arxiv.org/abs/2508.21273 · HTML: https://mlsanity.com/paper/2508.21273/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [Multivariate Time-series Anomaly Detection via Graph Attention Network](https://mlsanity.com/paper/2009.02040/) (2020)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation](https://mlsanity.com/paper/2502.12468/) (2025)
- [Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.15123/) (2024)
- [Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting](https://mlsanity.com/paper/2405.10216/) (2024)
- [Can Multimodal LLMs Perform Time Series Anomaly Detection?](https://mlsanity.com/paper/2502.17812/) (2025)
- [Financial Fine-tuning a Large Time Series Model](https://mlsanity.com/paper/2412.09880/) (2024)
- [TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection](https://mlsanity.com/paper/2508.00047/) (2025)

## Built on by (most cited first, 4 of 4)

- [Toward Reasoning-Centric Time-Series Analysis](https://mlsanity.com/paper/2510.13029/) (2025)
- [Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions](https://mlsanity.com/paper/2510.20102/) (2025)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [Can Large Language Models Reason about Event-Time Stream-Processing Semantics?](https://mlsanity.com/paper/2608.12348/) (2026)

## Abstract (arXiv)

The detection of anomalies in non-stationary time-series streams is a critical but challenging task across numerous industrial and scientific domains. Traditional models, trained offline, suffer significant performance degradation when faced with concept drift, where the underlying statistical properties of the data change over time. This paper introduces CALM (Continuous, Adaptive, and LLM-Mediated), a novel, end-to-end framework for real-time anomaly detection designed to address this challenge. CALM is built on the Apache Beam distributed processing framework and leverages the TimesFm foundation model for forecasting-based anomaly detection. The framework's novelty lies in two core contributions. First, it implements a closed-loop, continuous fine-tuning mechanism that allows the anomaly detection model to adapt to evolving data patterns in near real-time. Second, it introduces an LLM-as-a-Judge component, a Large Language Model that provides semantic, context-aware judgments on detected anomalies to curate a high-quality training dataset, deciding whether an anomaly represents transient noise or a meaningful pattern shift. We evaluate CALM on the comprehensive TSB-UAD benchmark. Our results demonstrate that the continuously fine-tuned model improves the ROC AUC score in most datasets compared to the static, pre-trained base model, validating the efficacy of our adaptive, LLM-guided approach to maintaining high-performance anomaly detection in dynamic streaming environments.