Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning

2026-02-08

AI Summary

This work addresses key limitations of current large language models in time-series reasoning—namely, the scarcity of high-quality chain-of-thought (CoT) training data, inefficient data scheduling strategies, and reinforcement learning algorithms ill-suited to temporal reasoning tasks. To overcome these challenges, the authors propose VeriTime, a novel framework that first constructs the first verifiable, multimodal time-series–text CoT dataset. It then introduces a task-difficulty-aware hierarchical data scheduling mechanism and a two-stage, fine-grained multi-objective reinforcement fine-tuning approach that leverages process-level CoT signals to guide optimization. Experimental results demonstrate that VeriTime substantially enhances the performance of small-scale models (3B/4B parameters) across diverse time-series reasoning benchmarks, achieving parity with or even surpassing that of large proprietary models.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Temporal Planning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in large language models (LLMs), especially their reasoning abilities unlocked through reinforcement learning (RL), have opened new opportunities for tackling tasks with long Chain-of-Thought (CoT) reasoning. However, leveraging LLM reasoning for time series remains in its infancy, hindered by the absence of carefully curated time series CoT data for training, limited data efficiency caused by underexplored data scheduling, and the lack of RL algorithms tailored for exploiting such time series CoT data. In this paper, we introduce VeriTime, a framework that tailors LLMs for time series reasoning through data synthesis, data scheduling, and RL training. First, we propose a data synthesis pipeline that constructs a TS-text multimodal dataset with process-verifiable annotations. Second, we design a data scheduling mechanism that arranges training samples according to a principled hierarchy of difficulty and task taxonomy. Third, we develop a two-stage reinforcement finetuning featuring fine-grained, multi-objective rewards that leverage verifiable process-level CoT data. Extensive experiments show that VeriTime substantially boosts LLM performance across diverse time series reasoning tasks. Notably, it enables compact 3B, 4B models to achieve reasoning capabilities on par with or exceeding those of larger proprietary LLMs.

Problem

• time series reasoning
• Chain-of-Thought
• large language models
• data synthesis
• reinforcement learning

Innovation

• Time Series Reasoning
• Process-Verifiable CoT
• Data Synthesis
• Data Scheduling
• Reinforcement Fine-tuning