Nexus：時間序列預測的智能體框架

摘要

時間序列預測不僅是數值外推，通常還需要結合新聞或事件等非結構化上下文資訊進行推理。雖然專門的時序基礎模型（TSFMs）擅長基於數值模式進行預測，但它們對現實世界的文字訊號缺乏感知。相反地，雖然大型語言模型（LLMs）正逐漸成為零樣本預測器，但其表現仍因領域和上下文基礎程度不同而參差不齊。為了解決這個差距，我們提出了Nexus——一個多智能體預測框架。該框架將預測任務分解為專門化的階段：分別處理宏觀與微觀層面的時間波動、在可用時整合上下文資訊，最終綜合生成預測結果。這種分解使Nexus能從季節性訊號適應到波動劇烈、由事件驅動的資訊，而不需依賴外部統計錨點或單一提示。我們證明，當前世代的LLM擁有比先前認知更強大的內在預測能力，而其關鍵取決於數值與上下文推理如何組織。在嚴格晚於LLM知識截止日期的數據（涵蓋Zillow房地產指標與波動劇烈的股票市場權益）上的評估顯示，Nexus始終能達到或超越最先進的TSFM與強大的LLM基準。除了數值準確性外，Nexus還能生成高品質的推理軌跡，明確揭示每次預測背後的根本驅動力。我們的結果確立：現實世界的預測本質上是一個遠超序列建模範疇的能動推理問題。

English

Time series forecasting is not just numerical extrapolation, but often requires reasoning with unstructured contextual data such as news or events. While specialized Time Series Foundation Models (TSFMs) excel at forecasting based on numerical patterns, they remain unaware to real-world textual signals. Conversely, while LLMs are emerging as zero-shot forecasters, their performance remains uneven across domains and contextual grounding. To bridge this gap, we introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages: isolating macro-level and micro-level temporal fluctuations, and integrating contextual information when available before synthesizing a final forecast. This decomposition enables Nexus to adapt from seasonal signals to volatile, event-driven information without relying on external statistical anchors or monolithic prompting. We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized, depending critically on how numerical and contextual reasoning are organized. Evaluated on data strictly succeeding LLM knowledge cutoffs spanning Zillow real estate metrics and volatile stock market equities, Nexus consistently matches or outperforms state-of-the-art TSFMs and strong LLM baselines. Beyond numerical accuracy, Nexus produces high-quality reasoning traces that explicitly show the fundamental drivers behind each forecast. Our results establish that real-world forecasting is an agentic reasoning problem extending well beyond only sequence modeling.