Awesome Agentic Time Series

A curated collection of papers on Agentic Time Series.

Motivation | Scientific Question | Related Work | Citation

---

💡 Motivation

Current time series analysis paradigms face fundamental limitations:

❌ Traditional Paradigm	✅ Agentic Paradigm
Fixed, Single-step, Single-direction, Limited Static and one-shot — once trained, the model produces predictions in a single forward pass without any ability to revisit, refine, or adapt its reasoning process.	Adaptive, Interactive, Closed-loop, Cyclic Iterative perception, planning, action, reflection, and memory accumulation — enabling closed-loop and self-adaptive time series analysis.

🔬 Scientific Question

We formulate time series analysis as a sequential decision optimization and path search problem — moving beyond static model-centric prediction toward multi-step reasoning, tool-augmented decision-making, and experience-driven evolution.

---

📚 Related Work

Position

	Paper	Highlight	Links
1	Mingyue Cheng, Xiaoyu Tao, Qi Liu, Ze Guo, Enhong Chen. Position: Beyond Model-Centric Prediction — Agentic Time Series Forecasting	率先探索 Agentic Time Series Forecasting 范式的立场 paper。

Time Series Analysis

	Paper	Highlight	Links
1	Garza A, Rosillo R. TimeCopilot	通用时间序列分析智能体。
2	Zhao H, Zhang X, Wei J, et al. Timeseriesscientist: A General-Purpose AI Agent for Time Series Analysis	通用时间序列分析智能体。

Time Series Forecasting

	Paper	Highlight	Links
1	Xiaohan Zhang, Tian Gao, Mingyue Cheng*, Bokai Pan, Ze Guo, Yaguo Liu, Xiaoyu Tao. AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting	率先探索人机协同交互式时间序列预测范式。
2	Xiaoyu Tao, Mingyue Cheng, Chuang Jiang, Tian Gao, Huanjian Zhang, Yaguo Liu. Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting	首个基于多轮强化学习训练的时间序列预测智能体。
3	Xiaoyu Tao, Mingyue Cheng*, Ze Guo, Shuo Yu, Yaguo Liu, Qi Liu, Shijin Wang. MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning	率先探索基于经验积累与持续进化的时间序列预测范式。

Time Series Anomaly Detection

	Paper	Highlight	Links
1	Xiaoyu Tao, Yuchong Wu, Mingyue Cheng, Ze Guo, Tian Gao. AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning	—

---

📖 Citation

If you find this collection helpful, please consider citing our position paper:

@article{cheng2026atsf,
  title   = {Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting},
  author  = {Cheng, Mingyue and Tao, Xiaoyu and Liu, Qi and Guo, Ze and Chen, Enhong},
  journal = {arXiv preprint arXiv:2602.01776},
  year    = {2026}
}

---

If you notice missing papers or incorrect metadata, feel free to open an issue or submit a PR.