AI 中文总结
本研究提出CastFSR智能体框架，将上下文感知时间序列预测建模为快慢反思工作流，通过实验证明其在公共数据集上的表现优于代表性基线。
AI 中文摘要
时间序列预测是复杂系统决策的基础，未来动态不仅受历史观测值影响，还受不断演变的上下文特征影响。大型语言模型（LLMs）的最新进展已将预测从数值外推扩展到上下文感知推理。然而，现有方法往往缺乏明确机制来识别相关上下文、推理其影响，并根据时间和领域约束验证预测。在本研究中，我们提出CastFSR，一种将上下文感知预测表述为快慢反思工作流的智能体框架。在快速思考阶段，CastFSR对观测值进行分析并选择轻量级预测器以构建数据驱动的预测先验。在慢速审议阶段，它检索上下文证据、自适应确定信息性回溯窗口，并推理上下文如何重塑未来动态。在反思阶段，它迭代优化预测以确保时间、上下文和领域一致性。CastFSR支持使用现成LLMs的无训练推理，以及通过两阶段SFT（监督微调）和强化学习策略的高效部署，该策略可将其编排能力迁移到小型LLMs。在公共数据集上的大量实验表明，CastFSR始终优于代表性基线。我们的代码可在此https URL获取。
英文摘要
Time series forecasting is fundamental to decision-making in complex systems, where future dynamics are influenced not only by historical observations but also by evolving contextual features. Recent advances in large language models (LLMs) have extended forecasting beyond numerical extrapolation toward context-aware reasoning. However, existing approaches often lack explicit mechanisms to identify relevant contexts, reason about their impacts, and validate forecasts against temporal and domain constraints. In this work, we propose CastFSR, an agentic framework that formulates context-aware forecasting as a Fast--Slow--Reflect workflow. In fast thinking, CastFSR profiles observations and selects lightweight forecasters to construct a data-driven forecast prior. In slow deliberation, it retrieves contextual evidence, adaptively determines informative look-back windows, and reasons about how contexts reshape future dynamics. In reflection, it iteratively refines forecasts to ensure temporal, contextual, and domain consistency. CastFSR supports both training-free inference with off-the-shelf LLMs and efficient deployment through a two-stage SFT and reinforcement learning strategy that transfers its orchestration capability to compact LLMs. Extensive experiments on public datasets demonstrate that CastFSR consistently outperforms representative baselines. Our code is available at https://github.com/Xiaoyu-Tao/CastFSR.
