Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Wen, Yang, Wei, Cao, Defu, Zhang, Yizhou, Tang, Lumingyuan, Cai, Jie, Liu, Yan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.04047
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910117590466560
author Ye, Wen
Yang, Wei
Cao, Defu
Zhang, Yizhou
Tang, Lumingyuan
Cai, Jie
Liu, Yan
author_facet Ye, Wen
Yang, Wei
Cao, Defu
Zhang, Yizhou
Tang, Lumingyuan
Cai, Jie
Liu, Yan
contents Time series analysis is crucial in real-world applications, yet traditional methods focus on isolated tasks only, and recent studies on time series reasoning remain limited to either single-step inference or are constrained to natural language answers. In this work, we introduce TS-Reasoner, a domain-specialized agent designed for multi-step time series inference. By integrating large language model (LLM) reasoning with domain-specific computational tools and an error feedback loop, TS-Reasoner enables domain-informed, constraint-aware analytical workflows that combine symbolic reasoning with precise numerical analysis. We assess the system's capabilities along two axes: (1) fundamental time series understanding assessed by TimeSeriesExam and (2) complex, multi-step inference evaluated by a newly proposed dataset designed to test both compositional reasoning and computational precision in time series analysis. Experiments show that our approach outperforms standalone general-purpose LLMs in both basic time series concept understanding as well as the multi-step time series inference task, highlighting the promise of domain-specialized agents for automating real-world time series reasoning and analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04047
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
Ye, Wen
Yang, Wei
Cao, Defu
Zhang, Yizhou
Tang, Lumingyuan
Cai, Jie
Liu, Yan
Machine Learning
Artificial Intelligence
Time series analysis is crucial in real-world applications, yet traditional methods focus on isolated tasks only, and recent studies on time series reasoning remain limited to either single-step inference or are constrained to natural language answers. In this work, we introduce TS-Reasoner, a domain-specialized agent designed for multi-step time series inference. By integrating large language model (LLM) reasoning with domain-specific computational tools and an error feedback loop, TS-Reasoner enables domain-informed, constraint-aware analytical workflows that combine symbolic reasoning with precise numerical analysis. We assess the system's capabilities along two axes: (1) fundamental time series understanding assessed by TimeSeriesExam and (2) complex, multi-step inference evaluated by a newly proposed dataset designed to test both compositional reasoning and computational precision in time series analysis. Experiments show that our approach outperforms standalone general-purpose LLMs in both basic time series concept understanding as well as the multi-step time series inference task, highlighting the promise of domain-specialized agents for automating real-world time series reasoning and analysis.
title TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.04047