cs.LGNov 9, 2026

Learning Evidence-Grounded Reasoning for Context-Aware Time Series Forecasting

Authors: Xingpeng Gao, Mingyue Cheng, Daoyu Wang, Huajian Zhang, Xiaoyu Tao

Organizations: State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China

Abstract

LLM-driven time series forecasting has become increasingly promising by leveraging contextual features to generate future values directly or refine forecast priors. However, incorporating contextual features alone does not ensure that models can identify which features matter for forecasting and understand what they suggest about future dynamics. We argue that the fundamental challenge is how to extract predictive evidence from contextual features and when and how to leverage it to guide forecasting decisions. In this paper, we propose CastReasoner, an evidence-grounded reasoning model for context-aware time series forecasting. Specifically, CastReasoner uses a structured chain of thought (CoT) to extract predictive evidence from contextual features, infer the future dynamics suggested by this evidence, and assess these dynamics against the forecast prior to guide adaptive forecasting decisions. To enable this capability, we design a reasoning-centric two-stage post-training framework including supervised fine-tuning (SFT) and reinforcement learning (RL). First, we synthesize reasoning trajectories through controllable multi-teacher guidance and select high-quality ones using a novel student-aware difficulty metric. Second, we design fine-grained multi-objective rewards to further improve reasoning and forecasting. To address heterogeneous learning needs across domains in both stages, we introduce a convergence-guided data balancing strategy. Through this two-stage training, CastReasoner improves both reasoning quality and predictive accuracy. Extensive experiments across multi-domain forecasting benchmarks demonstrate that CastReasoner achieves superior forecasting performance.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CastFSR: Fast--Slow--Reflect Agentic Reasoning for Context-Aware Time Series Forecasting

    Aug 4, 2026Xiaoyu Tao, Mingyue Cheng, Bokai Pan +1Context-Aware Time Series ForecastingTime Series Forecasting

  2. OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning

    Sep 30, 2026Tony Chen, Timo Stoffregen, Maxwell Xu +8Temporal Reasoning in Language ModelsLLM-Based Time Series Forecasting

  3. AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Time Series Forecasting

    Nov 12, 2025Xiaohan Zhang, Tian Gao, Mingyue Cheng +5Time Series ForecastingLLM-Based Time Series Forecasting