LAFP uses MCTS so a frozen TSFM proposes forecast pieces and an LLM ranks and judges them against text, improving text-conditioned forecasts without retraining.
Language Models Still Struggle to Zero-shot Reason about Time Series
1 Pith paper cite this work, alongside 12 external citations. Polarity classification is still indexing.
1
Pith paper citing it
12
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models
LAFP uses MCTS so a frozen TSFM proposes forecast pieces and an LLM ranks and judges them against text, improving text-conditioned forecasts without retraining.