arXiv cs.AI· Tong Guan, Tianxiang Zhan, Shirui Pan, Ming Jin·· 13 小时前AI 评分31
重新审视时间序列预测中的智能体模型编排
Rethinking Agentic Model Orchestration for Time Series Forecasting
AI 导读
研究提出 FairAMO 受控评估协议，用冻结候选预测区分编排收益与候选模型本身强度。在 GIFT-Eval 上，最佳编排器相对最佳单一 TSFM 仅将 MASE 降低不到 6%，收益取决于候选互补性而非数量，增加冗余成员甚至会抵消增益，历史证据的价值也很快饱和。
正文 · 原文
Abstract:Time series foundation models (TSFMs) perform unevenly across forecasting tasks. Recent work uses agentic model orchestration (AMO) to select or combine TSFMs, often outperforming individual forecasters. Yet these gains may reflect stronger or more complementary candidates rather than better orchestration. To disentangle these effects, we introduce FairAMO, a controlled evaluation protocol with frozen candidate forecasts. Experiments on GIFT-Eval show that AMO improves accuracy, but its gains are bounded by the candidate TSFMs. The best orchestrators reduce MASE by less than 6% relative to the best single TSFM across all tasks. These gains depend on complementarity (different candidates excel on different tasks) rather than the number of candidates. Adding members yields diminishing returns, and a redundant member can erase these gains. The value of historical evidence also saturates quickly. A few recent windows capture all gains, and further history adds none. These findings separate system-level forecasting gains from the contribution of orchestration itself.
| Comments: | Accepted by the NeurIPS 2026 Workshop on Foundation Models for Temporal Systems (FMTS) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29504 [cs.LG] |
| (or arXiv:2610.29504v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29504 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tong Guan [view email]
[v1]
Wed, 21 Oct 2026 09:55:04 UTC (931 KB)
来源：arXiv cs.AI · arxiv.org