A two-stage SFT-plus-RL framework gives a 7B language model step-by-step time series reasoning and beats or matches specialized forecasters on most of nine datasets.
Evaluating system 1 vs. 2 reasoning approaches for zero-shot time series forecasting: A benchmark and insights
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
A two-stage SFT-plus-RL framework gives a 7B language model step-by-step time series reasoning and beats or matches specialized forecasters on most of nine datasets.