Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Xingjian, Lu, Junkai, Li, Zhengyu, Qiu, Xiangfei, Hu, Jilin, Guo, Chenjuan, Jensen, Christian S., Yang, Bin
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.13653
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909995592843264
author Wu, Xingjian
Lu, Junkai
Li, Zhengyu
Qiu, Xiangfei
Hu, Jilin
Guo, Chenjuan
Jensen, Christian S.
Yang, Bin
author_facet Wu, Xingjian
Lu, Junkai
Li, Zhengyu
Qiu, Xiangfei
Hu, Jilin
Guo, Chenjuan
Jensen, Christian S.
Yang, Bin
contents Time series data widely exist in real-world cyber-physical systems. Though analyzing and interpreting them contributes to significant values, e.g, disaster prediction and financial risk control, current workflows mainly rely on human data scientists, which requires significant labor costs and lacks automation. To tackle this, we introduce TimeART, a framework fusing the analytical capability of strong out-of-the-box tools and the reasoning capability of Large Language Models (LLMs), which serves as a fully agentic data scientist for Time Series Question Answering (TSQA). To teach the LLM-based Time Series Reasoning Models (TSRMs) strategic tool-use, we also collect a 100k expert trajectory corpus called TimeToolBench. To enhance TSRMs' generalization capability, we then devise a four-stage training strategy, which boosts TSRMs through learning from their own early experiences and self-reflections. Experimentally, we train an 8B TSRM on TimeToolBench and equip it with the TimeART framework, and it achieves consistent state-of-the-art performance on multiple TSQA tasks, which pioneers a novel approach towards agentic time series reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13653
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
Wu, Xingjian
Lu, Junkai
Li, Zhengyu
Qiu, Xiangfei
Hu, Jilin
Guo, Chenjuan
Jensen, Christian S.
Yang, Bin
Machine Learning
Time series data widely exist in real-world cyber-physical systems. Though analyzing and interpreting them contributes to significant values, e.g, disaster prediction and financial risk control, current workflows mainly rely on human data scientists, which requires significant labor costs and lacks automation. To tackle this, we introduce TimeART, a framework fusing the analytical capability of strong out-of-the-box tools and the reasoning capability of Large Language Models (LLMs), which serves as a fully agentic data scientist for Time Series Question Answering (TSQA). To teach the LLM-based Time Series Reasoning Models (TSRMs) strategic tool-use, we also collect a 100k expert trajectory corpus called TimeToolBench. To enhance TSRMs' generalization capability, we then devise a four-stage training strategy, which boosts TSRMs through learning from their own early experiences and self-reflections. Experimentally, we train an 8B TSRM on TimeToolBench and equip it with the TimeART framework, and it achieves consistent state-of-the-art performance on multiple TSQA tasks, which pioneers a novel approach towards agentic time series reasoning.
title TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
topic Machine Learning
url https://arxiv.org/abs/2601.13653