Conventional time series forecasting treats prediction as a model-centric, static, and single-pass problem. This framing proves fundamentally inadequate for complex, adaptive, multi-turn scenarios encountered in real-world deployments. We propose Agentic Time Series Forecasting (ATSF) — a principled framework that organizes forecasting as an iterative agentic workflow. Rather than optimizing a single model's predictive accuracy in isolation, ATSF enables forecasting systems to interact with tools, incorporate feedback from outcomes, and evolve through accumulated experience. We formalize the framework through five interconnected cognitive components — Perception, Planning, Action, Reflection, and Memory — and propose three concrete implementation paradigms: workflow-based design, agentic reinforcement learning, and hybrid agentic workflows. We conclude by outlining key research opportunities and open challenges to guide the community toward this new frontier.
Extracts task-relevant information from raw, noisy inputs. Adaptive rather than fixed preprocessing — determines what information matters for each specific context.
Formulates forecasting objectives and decomposes complex tasks into subtasks. Revised dynamically as new observations or feedback arrive.
Executes decisions through autonomous tool interaction. Forecasting is treated as one action within a broader action space, enabling integration of diverse methods.
Iteratively evaluates, interprets, and revises predictions. Supports self-judgment without requiring external supervision or ground-truth feedback.
Preserves reusable experience — patterns, strategies, failure cases — across instances. Hierarchical access at instance, task, and domain levels.
First position paper to formally define the ATSF paradigm, establishing a principled conceptual framework for agentic forecasting.
Rigorous characterization of why static, model-centric approaches fail in adaptive, multi-turn real-world forecasting scenarios.
Three concrete strategies spanning the interpretability–adaptability design space, with comparative analysis of mechanisms and trade-offs.
Comprehensive outline of open challenges and future research directions to guide the community toward this new frontier.
Structures forecasting as predefined sequences of cognitive steps using directed acyclic graphs (DAGs) or standard operating procedures. Organizes the five ATSF components into interpretable, deterministic pipelines.
Applies reinforcement learning to the decisions surrounding forecasting — objective planning, action selection, strategy revision — rather than to predictive models alone. Enables autonomous discovery of novel strategies.
Integrates explicit workflow design with localized reinforcement learning at specific decision points. Balances the stability of structured workflows with the adaptability of learned strategies.
A curated list of papers on agentic time series forecasting. Maintained alongside this 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} }