Harnessing Generalist Agents for Contextualized Time Series
This work addresses the need for end-to-end temporal reasoning workflows in real-world applications by enabling LLM agents to handle structured time series data within rich contexts.
TimeClaw is a framework that equips generalist LLM agents with runtime support for contextualized time series analysis, integrating executable temporal tools, experience-driven capability evolution, and episodic multimodal memory. It achieves improved performance across diverse benchmarks in energy, finance, weather, and traffic domains.
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.