arXiv AI August 28, 2026 By Yilong Chen, Xiao Qin, Chenghao Liu, Liang Wu, Noelle I. Samia, Kaize Ding

LLM Agents for Time-Series: A Survey

The survey reviews LLM-based agents tailored to time-series tasks, organizing them by problem type rather than technical components. It categorizes existing systems into forecasting and reasoning, augmentation and synthesis, anomaly detection and diagnosis, and decision support, and analyzes how task demands influence agent architecture, tool use, and memory design. The paper also summarizes datasets, environments, and compares model performance, providing a task-oriented guide and highlighting gaps for future research.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 2

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

arXiv:2606. 01498v1 Announce Type: cross Abstract: Time series data inform critical decisions across many real-world domains.

By Yaxuan Kong, Qingren Yao, Yuqi Nie, Yichen Li, Yilei Shao, Stefan Zohren, Anna Vettoruzzo, Joaquin Vanschoren, Ming Jin, Qingsong Wen

llms agents benchmarks

arXiv AI

Jun 2

Bridging the Last Mile of Time Series Forecasting with LLM Agents

arXiv:2606. 02497v1 Announce Type: new Abstract: Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation.

By Yuhua Liao, Zetian Wang, Qiangqiang Nie, Zhenhua Zhang

llms agents safety

arXiv Machine Learning

Jun 5

Harnessing Generalist Agents for Contextualized Time Series

arXiv:2606. 05404v1 Announce Type: cross Abstract: Time series are often embedded in rich contexts that are essential for holistic modeling.

By Zihao Li, Kaifeng Jin, Yuanchen Bei, Jiaru Zou, Avaneesh Kumar, Xuying Ning, Yanjun Zhao, Mengting Ai, Baoyu Jing, Hanghang Tong, Jingrui He

llms agents multimodal benchmarks

arXiv AI

Jun 30

An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations

arXiv:2606. 28467v1 Announce Type: cross Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility managers struggle to use.

By Dihia Falouz, Aida Douaibia, Amine Bechar, Youssef Elmir, Abbes Amira, Adel Oulefki

llms rag agents benchmarks

arXiv AI

Jun 11

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

arXiv:2509. 11575v3 Announce Type: replace Abstract: Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer.

By Ching Chang, Yidan Shi, Defu Cao, Wei Yang, Jeehyun Hwang, Haixin Wang, Jiacheng Pang, Wei Wang, Yan Liu, Wen-Chih Peng, Tien-Fu Chen

llms agents benchmarks safety

arXiv AI

Jun 16

Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft

arXiv:2606. 15684v1 Announce Type: new Abstract: We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks.

By Juheon Yi, Jinglu Wang, Xiaoyi Zhang, Yan Lu

llms agents benchmarks

One email a morning, machine-written

Related stories

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

Bridging the Last Mile of Time Series Forecasting with LLM Agents

Harnessing Generalist Agents for Contextualized Time Series

An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft