LLM Agents for Time-Series: A Survey

Yilong Chen; Xiao Qin; Chenghao Liu; Liang Wu; Noelle I. Samia; Kaize Ding

cs.AIAug 26, 2026

LLM Agents for Time-Series: A Survey

Authors: Yilong Chen, Xiao Qin, Chenghao Liu, Liang Wu, Noelle I. Samia, Kaize Ding

Organizations: Northwestern University · Datadog AI Research · Nokia

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.

Figures & tables

Figure 1: Task coverage and release timeline of 47 surveyed LLM-agent papers for time-series tasks.

Figure 2: An illustration of the main architectural patterns for time-series agent systems.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Survey	Year	TS-specific	LLM Agents	Forecasting & Reasoning	Augmentation & Synthesis	Anomaly Detection & Diagnosis	Decision Support	Taxonomy	Design Guidance
Jiang et al. (2024)	2024	Yes	No	$\checkmark$	$\sim$	$\checkmark$	$\sim$	Method-driven	Limited
Zhang et al. (2024b)	2024	Yes	No	$\checkmark$	$\checkmark$	$\checkmark$	$\times$	Method-driven	Limited
Chang et al. (2026)	2026	Yes	Partial	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	Topology-driven	Limited
Zhang et al. (2025c)	2025	Yes	Partial	$\checkmark$	$\checkmark$	$\checkmark$	$\sim$	Capability-driven	Limited
Ours	2026	Yes	Yes	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	Problem-driven	Yes

Appendix

Table 1: Comparison with related time-series LLM surveys.

\checkmark

: clearly covered;

\sim

: partially covered;

\times

: not covered.

Failure mode	Where it appears	Related work	Design choice	Implementation check
Error propagation across workflow stages	Forecasting and reasoning pipelines that pass outputs through diagnosis, model selection, context analysis, prediction, and validation	TimeSeriesScientist Zhao et al. (2025) ; CLIMATEAGENT Kim et al. (2025) ; CastFlow Pan et al. (2026)	Keep stage outputs explicit. Log retrieved evidence, tool calls, predictions, and validation results so later stages do not inherit hidden errors	Can a reader inspect the artifact used by the next stage?
Numerical or domain reasoning errors	Tasks that require temporal structure, metadata, domain conventions, or quantitative operations	TS-Agent Liu et al. (2025) ; TS-Reasoner Ye et al. (2024b) ; CLIMATEAGENT Kim et al. (2025)	Let the LLM plan and explain, but move calculation and domain-specific parsing into tools, operators, or specialist agents	Can the numerical claim be rerun outside the LLM?
Semantic drift in generated data	Augmentation and synthesis, where plausible-looking outputs can break trend, periodicity, local shape, correlation, or domain constraints	DCATS Yeh et al. (2025) ; MERIT Zhou et al. (2025) ; BRIDGE Li et al. (2025)	Generate from target context and verify temporal properties before the synthetic data enters training or evaluation	Do checks cover trend, seasonality, local shape, and correlation rather than textual plausibility alone?
Brittle LLM-as-judge validation	Validation settings where a pretrained judge can approve an output without task evidence or executable checks	DCATS Yeh et al. (2025) ; TS-Reasoner Ye et al. (2024b)	Treat LLM critique as one signal. Require task metrics, execution feedback, or downstream validation before accepting an output	Would the output be rejected if another LLM approved it but the executable check failed?
Contamination during online updates	Streaming anomaly detection, where transient anomalies can be absorbed as the new normal	CALM Devireddy and Huang (2025)	Separate alarm decisions from update decisions; gate which observations can enter memory or fine-tuning data	Can short-lived anomalies be kept out of the update set?
Unsafe or infeasible actions in closed-loop control	Traffic and grid-control agents that issue executable actions under operational constraints	LLMLight Lai et al. (2025) ; Grid-Agent Zhang et al. (2025d) ; GridMind Jin et al. (2025)	Check proposed actions with a simulator, solver, feasibility test, or safety validator before execution	Does every action pass an environment or constraint check first?

Appendix

Table 2: Summary of documented failure modes for time-series agent systems. Each failure mode is linked to related work, design choices, and implementation checks.

Method	Year	Source	Problem Type	Architecture	Tools	Memory
TimeSeriesScientist Zhao et al. (2025)	2025	arXiv	Forecasting	Multi (Cooperative)	Stat./ML Models	Evidence Logs
TimeXL Jiang et al. (2025)	2025	NeurIPS	Forecasting	Multi (Cooperative)	None	Evidence Logs, Pattern Library
TimeCAP Lee et al. (2025)	2025	AAAI	Forecasting	Multi (Cooperative)	Data Processing Tools	Pattern Library
NewsTSForecasting Zhang et al. (2025e)	2025	arXiv	Forecasting	Multi (Competitive)	Search & Retrieval APIs	Evidence Logs, Analysis Strategies
TRACE Chen and Xie (2025)	2025	IEEE TAI	Forecasting	Multi (Competitive)	None	Evidence Logs
FLAIRR-TS Jalori et al. (2025)	2025	EMNLP Findings	Forecasting	Multi (Cooperative)	None	Evidence Logs, Analysis Strategies

Appendix

Table 3: Summary of representative LLM-based agentic methods for time-series tasks. Each method is grouped by Problem Type and further characterized by its publication year, venue or source, architecture, tools, and memory.

Task Family	Architecture	Tools	Memory
Forecasting & Reasoning ( $n=14$ )	Single: 2 (14.3%); Multi (Cooperative): 8 (57.1%); Multi (Competitive): 3 (21.4%); Multi (Mixed): 1 (7.1%)	Database APIs: 3 (21.4%); Search & Retrieval APIs: 2 (14.3%); Data Processing Tools: 8 (57.1%); Stat./ML Models: 5 (35.7%); Simulators, Solvers & Optimizers: 1 (7.1%); None: 4 (28.6%)	Evidence Logs: 10 (71.4%); Pattern Library: 6 (42.9%); Analysis Strategies: 3 (21.4%); None: 0 (0%)
Augmentation & Synthesis ( $n=6$ )	Single: 1 (16.7%); Multi (Cooperative): 4 (66.7%); Multi (Competitive): 0 (0%); Multi (Mixed): 1 (16.7%)	Database APIs: 1 (16.7%); Search & Retrieval APIs: 1 (16.7%); Data Processing Tools: 3 (50.0%); Stat./ML Models: 4 (66.7%); Simulators, Solvers & Optimizers: 0 (0%); None: 1 (16.7%)	Evidence Logs: 1 (16.7%); Pattern Library: 1 (16.7%); Analysis Strategies: 0 (0%); None: 4 (66.7%)
Anomaly Detection & Diagnosis ( $n=8$ )	Single: 3 (37.5%); Multi (Cooperative): 4 (50.0%); Multi (Competitive): 0 (0%); Multi (Mixed): 1 (12.5%)	Database APIs: 2 (25.0%); Search & Retrieval APIs: 1 (12.5%); Data Processing Tools: 8 (100%); Stat./ML Models: 7 (87.5%); Simulators, Solvers & Optimizers: 0 (0%); None: 0 (0%)	Evidence Logs: 5 (62.5%); Pattern Library: 1 (12.5%); Analysis Strategies: 2 (25.0%); None: 2 (25.0%)
Decision Support ( $n=19$ )	Single: 6 (31.6%); Multi (Cooperative): 8 (42.1%); Multi (Competitive): 2 (10.5%); Multi (Mixed): 3 (15.8%)	Database APIs: 3 (15.8%); Search & Retrieval APIs: 5 (26.3%); Data Processing Tools: 9 (47.4%); Stat./ML Models: 5 (26.3%); Simulators, Solvers & Optimizers: 9 (47.4%); None: 1 (5.3%)	Evidence Logs: 10 (52.6%); Pattern Library: 5 (26.3%); Analysis Strategies: 4 (21.1%); None: 4 (21.1%)

Appendix

Table 4: Within-family counts and percentages of architecture, tool, and memory choices among the 47 systems summarized in Table 3 . Tool and memory categories are non-exclusive.

Figure 4: Typical design patterns of time-series agent systems across representative tasks. From top left to bottom right, the panels correspond to forecasting, reasoning, augmentation, synthesis, anomaly detection, diagnosis, trading, and traffic and grid control.

Resource	Category	Problem Type	Interactive	Timesteps	Series	Latest Release
Forecasting
M4 Makridakis et al. (2018)	Benchmark	Forecasting	No	Up to 10k	$\sim$ 100k	2018
M5 Makridakis et al. (2022)	Benchmark	Forecasting	No	1.9k	42k	2020
MIRAI Ye et al. (2024a)	Benchmark	Forecasting	No	$\sim$ 1M	59k	2025
FutureX Zeng et al. (2025)	Benchmark	Forecasting	No	Live/Daily	195 sources	2025
Monash TSF Godahewa et al. (2021)	Dataset Repo	Multi-Domain Forecasting	No	Up to 527k	Up to 145k	2021

Appendix

Table 5: Summary of representative resources for time-series tasks. Each resource is grouped by Problem Type and further characterized by its type, interactivity, temporal scale, number of series, and latest release.

Task	Dataset	Metric	Method	Score
ETTh1 forecasting Zhou et al. (2021)
Forecasting	ETTh1	MAE	FLAIRR-TS Jalori et al. (2025)	0.101
Forecasting	ETTh1	MAE	LSTP Liu et al. (2024a)	0.150
Forecasting	ETTh1	MAE	DLinear Zeng et al. (2023)	0.390
Forecasting	ETTh1	MAE	Agentic-RAG (Llama3-8B) Ravuru et al. (2024)	0.396
Forecasting	ETTh1	MAE	GPT4TS Zhou et al. (2023)	0.397

Appendix

Table 6: Comparable quantitative evidence across time-series tasks (Part 1). Agent methods are highlighted in bold.

Task	Dataset	Metric	Method	Score
Yahoo anomaly detection Laptev (2015)
Anomaly detection	Yahoo	F1	MERIT (Llama3.1-8B) Zhou et al. (2025)	0.905
Anomaly detection	Yahoo	F1	TimesURL Liu and Chen (2024)	0.892
Anomaly detection	Yahoo	F1	TS2Vec Yue et al. (2022)	0.885
Anomaly detection	Yahoo	F1	SR Ren et al. (2019)	0.879
Anomaly detection	Yahoo	F1	DONUT Xu et al. (2018)	0.873

Appendix

Table 7: Comparable quantitative evidence across time-series tasks (Part 2). Agent methods are highlighted in bold.

LLM-Based Time Series Anomaly Detection

See all 11 papers

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
May 31, 2026Yaxuan Kong, Qingren Yao, Yuqi Nie +7Time Series Reasoning LLM Agent Evaluation
University of Oxford · VulpiVox Intelligence · Eindhoven University of Technology +3
TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale
Apr 11, 2026Malgorzata Gwiazda, Yifu Cai, Mononito Goswami +2Time Series Reasoning LLM Evaluation
Technical University of Munich, Munich, Germany · Auton Lab, School of Computer Science, Carnegie Mellon University, Pittsburgh, US
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
Aug 25, 2025Bingxi Zhao, Lin Geng Foo, Ping Hu +3Multi-Agent LLM Systems LLM Agents

May 31, 2026J/K move · Enter open · S save

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

Yaxuan Kong, Qingren Yao, Yuqi Nie, Yichen Li+6

University of Oxford · VulpiVox Intelligence · Eindhoven University of Technology+3

Time Series Reasoning LLM Agent Evaluation Agent Evaluation AI Agent Benchmarks

Open paper AskPDF arXiv

Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural language and tools, it remains unclear whether they can conduct reliable time series analysis across multi-turn conversations. Existing benchmarks focus on single-step tasks such as forecasting and anomaly detection, overlooking practical workflows where user goals evolve, agents must build on prior analyses, and conclusions emerge from accumulated evidence. In this work, we introduce TimeSage-MT, a multi-turn benchmark for agentic time series reasoning with 240 tasks and 2,680 dialogue turns across 8 real-world domains, spanning basic exploration to decision-oriented analysis. TimeSage-MT is built through a reproducible pipeline that converts real-world time series data into multi-turn conversations with verifiable answers. It provides a unified evaluation protocol and public leaderboard for comparing time series agentic systems. To demonstrate the benchmark's utility, we evaluate frontier LLMs alongside TimeSage, a novel structured agent equipped with a comprehensive time series skill library. The results show sharp performance drops on decision-oriented tasks, driven by failures in memory, uncertainty handling, and domain-based decision making. TimeSage-MT exposes critical gaps in current agentic reasoning and provides a rigorous foundation for future development.

Abstract

LLM-Based Time Series Anomaly Detection

Explore similar work

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale

LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios