让大模型更懂时间序列，实现带上下文的智能分析
Harnessing Generalist Agents for Contextualized Time Series
- 给通用大模型配备专用于时间序列的运行支持工具
- 在能源、金融、交通等多领域任务中表现优于传统方法
- 适合需要端到端时序分析的工业场景开发者
时间序列常伴随丰富上下文，对整体建模至关重要。现实中的从业者往往需要端到端的工作流来分析时序动态，而广受研究的预测任务只是其中一环。尽管通用人工智能代理为复杂上下文下的工作流提供了前景，但它们仍主要在文本空间中运作，与结构化时序信号不完全对齐。本文提出TimeClaw，一种面向时间序列的代理框架，赋予通用大语言模型所需的时序原生运行时支持，以实现上下文感知的时间推理。TimeClaw集成可执行的时序工具，实现有根基且可审计的分析；基于经验的能力演化机制，构建可复用的分析流程；以及情景式多模态记忆，用于检索相关推理轨迹。这些组件共同实现了被充分激发的开放性时序推理能力。在涵盖能源、金融、天气、交通等多个真实世界领域的多个基准上的广泛评估显示，TimeClaw性能显著提升。代码已开源：https://github.com/iDEA-iSAIL-Lab-UIUC/TimeClaw。
原文摘要 · Abstract (English)
Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end workflows for analyzing temporal dynamics, where widely studied tasks such as forecasting are only one step in a broader solution loop. While generalist AI agents offer a promising interface for such workflows under complex contexts, they still operate primarily in textual spaces that are not fully aligned with structured temporal signals. In this work, we introduce TimeClaw, an agentic harness framework for time series that equips generalist LLM agents with the time series-native runtime support needed for contextualized temporal reasoning. TimeClaw integrates executable temporal tools for grounded and auditable analysis, experience-driven capability evolution for creating reusable analytical routines, and episodic multimodal memory for retrieving relevant reasoning traces. Together, these components unlock harnessed open-ended temporal reasoning with contextual information. Extensive evaluation on multiple benchmarks covering diverse tasks across energy, finance, weather, traffic, and other real-world domains demonstrates improved performance of TimeClaw. Code is available at https://github.com/iDEA-iSAIL-Lab-UIUC/TimeClaw.
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。