[2605.00015] TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning

Electrical Engineering and Systems Science > Signal Processing arXiv:2605.00015 (eess) [Submitted on 18 Apr 2026] Title:TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning Authors:Siyang Li, Yize Chen, Zijie Zhu, Yuxin Pan, Yan Guo, Ming Huang, Hui Xiong View a PDF of the paper titled TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning, by Siyang Li and 6 other authors View PDF HTML (experimental) Abstract:Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking when adapting to specific downstream forecasting tasks for two reasons. First, the non-stationary and uncertain nature of time series data lead to inevitable temporal distribution shifts between historical training and future testing data, while current Supervised FineTuning (SFT)-based methods are prone to overfitting and may degrade generalization. Second, training data availability varies across forecasting tasks, requiring TSFMs to generalize well under diverse data regimes. To address these challenges, we introduce the Time series Reinforcement Finetuning (TimeRFT) paradigm for TSFM downstream adaptation, which consists of two task-specific training recipes: i) A forecasting quality-based temporal reward mechanism that conducts a multi-faceted evaluation of the contribution of each prediction step to overall f...