Time Series QA

QA: Question Answering

Time-series question answering studies how systems can answer questions about trends, events, intervals, and forecasts in data collected over time, making signals easier to use in settings such as medicine, finance, and incident response. Approaches include aligning time-series encoders with language models, representing signals as structured events, and using tools for retrieval, numerical computation, or forecasting. Benchmarks increasingly test temporal localization, long contexts, irregular sampling, and multimodal evidence across clinical, industrial, and financial data. A central challenge is ensuring answers are grounded in the relevant observations: strong aggregate scores can hide errors in evidence use, temporal reasoning, and tool coordination.

Latest papers

32 papers5 papers in the last four weeks, down 29% on the four weeks before. 0.0% of all new papers.

TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
Jan 20, 2026Xingjian Wu, Junkai Lu, Zhengyu Li +5Time Series Reasoning Time Series QA
East China Normal University, Shanghai, China · Aalborg University, Aalborg, Denmark
QuAnTS: Question Answering on Time Series
Nov 7, 2025Felix Divo, Maurice Kraus, Anh Q. Nguyen +5Time Series QA
AI & ML Lab, TU Darmstadt · University of New South Wales · MBZUAI, Abu Dhabi +4

Jan 20, 2026J/K move · Enter open · S save

TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation

Xingjian Wu, Junkai Lu, Zhengyu Li, Xiangfei Qiu+4

East China Normal University, Shanghai, China · Aalborg University, Aalborg, Denmark

Time Series Reasoning Time Series QA Agentic Reasoning LLM Tool Use

Open paper AskPDF arXiv

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.

Latest papers

TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation

QuAnTS: Question Answering on Time Series