TFRBench is a new benchmark and multi-agent synthesis method that generates reasoning traces for time-series forecasting and shows these traces raise average accuracy from ~40% to ~57% when used to prompt LLMs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
STRIDE injects distilled LLM reasoning as continuous cross-modal priors into TSFMs via mean-pooled hidden states, achieving SOTA forecasting (0.674 MASE, 0.454 CRPS) on GIFT-Eval and superior reasoning on TFRBench.
citing papers explorer
-
TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
TFRBench is a new benchmark and multi-agent synthesis method that generates reasoning traces for time-series forecasting and shows these traces raise average accuracy from ~40% to ~57% when used to prompt LLMs.
-
Reasoning-Aware Training for Time Series Forecasting
STRIDE injects distilled LLM reasoning as continuous cross-modal priors into TSFMs via mean-pooled hidden states, achieving SOTA forecasting (0.674 MASE, 0.454 CRPS) on GIFT-Eval and superior reasoning on TFRBench.