发表机构
Northwestern University; Datadog AI Research; Nokia（西北大学; Datadog人工智能研究院; 诺基亚）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述针对LLM智能体在时间序列问题上设计差异大的问题，采用问题驱动分类法梳理现有系统，分析任务对架构等的影响，对比模型性能，为相关设计提供指南并指出未来缺口。
AI 中文摘要
基于大语言模型（LLM）的智能体正被越来越多地开发用于解决时间序列问题，但其设计选择在不同任务场景中差异显著。本综述采用问题驱动的分类法，按所解决的时间序列问题而非孤立技术组件来组织这些系统，将现有系统分为四类：预测与推理、增强与合成、异常检测与诊断、决策支持。在每一类中，我们考察任务需求如何影响智能体架构、工具使用和记忆设计。我们还总结了代表性数据集与环境，并在相同或相近场景下对比了报告的模型性能。总体而言，本综述为设计面向时间序列问题的LLM智能体提供了面向任务的指南，并指出了未来工作的开放缺口。
英文摘要
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.
CommentsAccepted to Findings of EMNLP 2026
