arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.04047cs.LGcs.AI
收藏

TS-Reasoner: 面向领域的时序推理代理用于推理和自动化分析

TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis

Wen Ye, Wei Yang, Defu Cao, Yizhou Zhang, Lumingyuan Tang, Jie Cai, Yan Liu

AI总结:

本文提出TS-Reasoner,一种面向领域的时序推理代理,结合大语言模型与领域工具,实现多步推理和约束感知分析,实验表明其在时序理解与多步推理任务中优于通用LLM。

摘要:

时序分析在现实应用中至关重要,但传统方法仅关注孤立任务,近期研究多局限于单步推理或自然语言回答。本文引入TS-Reasoner,一种面向领域的代理,通过整合大语言模型推理、领域专用计算工具和误差反馈循环,实现领域引导、约束感知的分析流程,结合符号推理与精确数值分析。我们沿两个轴评估系统能力:(1) 通过TimeSeriesExam评估基础时序理解;(2) 通过新提出的测试集评估复杂多步推理中的组合推理和计算精度。实验表明,我们的方法在基础时序概念理解和多步时序推理任务中均优于通用LLM,凸显了领域专用代理在自动化现实时序推理和分析中的潜力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑