Jul 2026
LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models
Experiments on Context-is-Key and Time-MMD across two TSFM backbones (Chronos and TimesFM) and four LLMs show that \rc{} delivers consistent improvements across model choices, supporting sequential search as an effective training-free approach to text-conditioned forecasting.
H. Nguyen, Dung Nguyen, M. Nguyen et al.
· arXiv.org · 0 citations