做时间序列预测的团队终于有了一个能处理业务上下文的实用方案——LLM Agent 自动整合节假日、活动等非结构化信息，让统计预测直接变成决策可用的结果，值得做预测的开发者点开看看。
时间序列预测在基础模型支持下取得了快速进展，但统计预测结果往往需要结合业务上下文（如节假日、活动计划、外部事件等）才能成为决策就绪的预测。本文提出了“最后一公里预测”问题，并设计了一个基于 LLM Agent 的框架，该框架在预测模型之上运行，维护统一的工作空间，调用工具检索上下文证据，并在结构安全约束下将推理轨迹转化为显式的预测修订动作。系统还支持通过 map-reduce 分解进行长周期预测，并通过记忆库进行事后反思，确保可控和可审计。实际案例表明，LLM Agent 能有效弥合统计预测与业务就绪预测之间的差距。
Bridging the Last Mile of Time Series Forecasting with LLM Agents
Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation. However, in real-world forecasting settings, a statistically plausible baseline is rarely the final forecast used in practice. Before a forecast becomes decision-ready, it often needs to be revised using weakly structured business context such as holiday effects, campaign plans, external events, historical analogs, and expert feedback. This practical stage remains underexplored in the forecasting literature. In this paper, we formulate this stage as the \textbf{last-mile forecasting} problem and present an LLM-agent framework that sits on top of a forecasting backbone. Our system maintains a unified forecast workspace, invokes tools to retrieve contextual evidence, and converts reasoning trajectories into explicit forecast revision actions under structural safety constraints. It also supports long-horizon forecasting through map-reduce-style decomposition and post-hoc reflection through a memory bank. The resulting system is designed to be controllable and auditable. Through real-world case studies, we show how LLM agents can bridge the gap between statistical prediction and business-ready forecasting.