PapersSelected72°5月20日 15:08

Google Nexus 论文：预测需理解事件，多 agent 拆解时间序列

AI Will@FinanceYF5

Post

View the post

Why we picked it

做时间序列预测的团队终于有了新思路——Nexus 把事件理解引入预测，MAPE 降低 86.6% 的效果值得在业务中试试。

Google 新论文 Nexus 提出，时间序列预测不应仅依赖历史曲线，还需理解背后的事件。该方法将预测任务拆分为多个 agent：整理事件、判断环境、追踪冲击和综合校准。

Body

在 Zillow 数据集测试中，使用 Claude 的 Nexus 版本比普通 CoT 提示平均 MAPE 降低 86.6%。

这标志着预测模型从单纯画曲线转向解释曲线为何变动，为金融、房地产等领域提供更可解释的预测。

Original · AI Will

Google 新论文 Nexus 认为：预测不该只看历史曲线，还要理解背后的事件。它把时间序列预测拆成多个 agent：整理事件、判断环境、追踪冲击、综合校准。在 Zillow 测试中，Claude 版本比普通 CoT 提示平均 MAPE 降低 86.6%。未来预测模型不只是画曲线，而是解释曲线为什么会动。📊 1 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Key entities and technical topics under continuous tracking include 时间序列预测, 多智能体, 事件驱动, Google.

Source attribution: curated from AI Will (@FinanceYF5).

#时间序列预测 #多智能体 #事件驱动 #Google #Claude

Keep reading

Recent stories with the same tag or section

Papers BuildersSelected01:31

GIFT-Eval-CTX Benchmark Tests LLMs on Contextual Forecasting

The non-obvious takeaway is that an LLM layered over a specialised forecasting model beats both pure LLMs and pure statistical models, suggesting a hybrid architecture is the practical path for time-series work. Teams building demand planning, energy load, or capacity forecasting tools can use the open benchmark to validate whether their pipelines actually exploit textual context. Practitioners comparing agent frameworks for forecasting should benchmark MoiraiAgent's pattern of pairing an LLM with code execution and a domain model against their own stack.

#GIFT-Eval-CTX #MoiraiAgent #GPT-5.6 Sol #Claude Opus 4.8