Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs

Excerpt

arXiv:2602.12756v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. Existing approaches typically employ an autoregressive generation strategy to adapt LLMs for TSF. However, we identify a theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, recursively consuming its own