Does More History Help? Understanding Context Length in Time-Series Foundation Models

*Time series foundation models* (TSFMs) for time series forecasting are designed to operate on variable input context lengths. This leads to the question: *how much context is worth using for a given task?* While the current trend favors longer contexts to enable more flexible predictors, their beneficial effect on inference-time accuracy is not guaranteed. In this work, we systematically investigate the influence of context length on forecasting performance across $11$ state-of-the-art TSFMs, and show consistent diminishing returns as the context length grows: an effect called *context saturation*. Through experiments in controlled environments, we provide insight into the factors driving context saturation, and show signs of recency bias in TSFMs, where their ability to leverage long-range dependencies varies substantially by model. Furthermore, through oracle context-length selection, we demonstrate the existence of operating points with both lower aggregate forecasting error and lower computational cost than those resulting from maximum context length. Finally, we propose a methodology for *zero-shot* inference-time context length selection, leveraging only synthetic data. Evaluated across all $11$ TSFMs on the GiftEval benchmark, our approach achieves substantial efficiency gains, validating the practical impact of our findings.