LLM Agents for Time-Series: A Survey
cs.AI
Submitted: 2026-08-26
Updated: 2026-08-26
Comments: Accepted to Findings of EMNLP 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: LLM-based agents are increasingly being developed for time-series problems, but their design choices vary substantially across task settings.
Terminology
Abstract
LLM-based agents are increasingly being developed for time-series problems, but their design choices vary substantially across task settings. This survey adopts a problem-driven taxonomy that organizes these systems by the time-series problems they address rather than by isolated technical components. We group existing systems into four categories: forecasting and reasoning, augmentation and synthesis, anomaly detection and diagnosis, and decision support. Within each category, we examine how task requirements shape agent architecture, tool use, and memory design. We further summarize representative datasets and environments, and compare reported model performance under shared or closely related settings. Overall, this survey offers a task-oriented guide to designing LLM-based agents for time-series problems and identifies open gaps for future work.
Sources
- GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents
- Merlion: A Machine Learning Library for Time Series
- TimeSeriesExam: A time series understanding exam
- TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
- StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting
- Nexus : An Agentic Framework for Time Series Forecasting
- CALM: A Framework for Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streams
- From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
- Monash Time Series Forecasting Archive
- Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models
- A Dual Large Language Models Architecture with Herald Guided Prompts for Parallel Fine Grained Traffic Signal Control
- CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Control
- Large Language Model based Multi-Agents: A Survey of Progress and Challenges
- Continual Learning, Not Training: Online Adaptation For Agents
- HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?
- Empowering Time Series Analysis with Large Language Models: A Survey
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems