让大模型像专家一样自动分析时间序列数据，提升预测与决策效率。
TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
- 结合大模型推理与工具调用能力，构建可自主分析的时间序列智能体。
- 在10万条专家操作轨迹上训练，实现80亿参数模型在多任务上领先表现。
- 适合需要自动化时间序列分析的工业、金融等场景，推动智能决策落地。
时间序列数据广泛存在于真实世界的网络物理系统中。尽管其分析与解释具有重大价值（如灾害预测、金融风险控制），但当前工作流程仍高度依赖人工数据科学家，成本高昂且缺乏自动化。为此，我们提出TimeART框架，融合强工具的分析能力与大语言模型（LLM）的推理能力，作为全自主的时序问答（TSQA）数据科学家。为训练基于LLM的时序推理模型（TSRM）掌握策略性工具使用，我们构建了包含10万条专家操作轨迹的TimeToolBench数据集。为进一步提升泛化能力，我们设计四阶段训练策略，使模型通过早期经验与自我反思持续优化。实验中，在TimeToolBench上训练80亿参数的TSRM并接入TimeART框架后，其在多个TSQA任务上均达到一致的最先进水平，开创了面向自主式时间序列推理的新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。