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

• URL: http://arxiv.org/abs/2602.07830v1
• Date: Sun, 08 Feb 2026 05:42:35 GMT
• Title: Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
• Authors: Jiahui Zhou, Dan Li, Boxin Li, Xiao Zhang, Erli Meng, Lin Li, Zhuomin Chen, Jian Lou, See-Kiong Ng,
• Abstract summary: We introduce VeriTime, a framework that tailors large language models for time series reasoning through data synthesis, data scheduling, and RL training.<n>Extensive experiments show that VeriTime substantially boosts LLM performance across diverse time series reasoning tasks.
• Score: 46.72047865932384
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning [17.69077698133793]
  Time series reasoning is crucial to decision-making in diverse domains, including finance, energy usage, traffic, weather, and scientific discovery.<n>LLMs often struggle with the numerical understanding of time series data.<n>We develop a training recipe that applies instruction finetuning after the alignment pretraining.
  arXiv  Detail & Related papers  (2025-10-03T21:20:54Z)
• Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning [2.426309874608745]
  Complex numerical time series analysis often demands multi-step reasoning capabilities beyond current models' reach.<n>We introduce Chain Of thought for Understanding Numerical Time Series (COUNTS), the first framework that trains large language models to perform Chain-of-Thought (CoT) reasoning across diverse time series tasks using reinforcement learning (RL) with verifiable rewards.<n>Our experiments demonstrate that this RL-driven approach with intermediate CoT reasoning significantly enhances LLM performance across various time series analysis tasks, opening new possibilities for complex temporal data reasoning.
  arXiv  Detail & Related papers  (2025-10-01T17:02:28Z)
• LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics [56.99021951927683]
  Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring.<n>Existing Large Language Models (LLMs) usually perform suboptimally because they neglect the inherent characteristics of time series data.<n>We propose LLM-PS to empower the LLM for TSF by learning the fundamental textitPatterns and meaningful textitSemantics from time series data.
  arXiv  Detail & Related papers  (2025-03-12T11:45:11Z)
• Large Language Models are Few-shot Multivariate Time Series Classifiers [23.045734479292356]
  Large Language Models (LLMs) have been extensively applied in time series analysis.<n>Yet, their utility in the few-shot classification (i.e., a crucial training scenario) is underexplored.<n>We aim to leverage the extensive pre-trained knowledge in LLMs to overcome the data scarcity problem.
  arXiv  Detail & Related papers  (2025-01-30T03:59:59Z)
• ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning [10.854285913078257]
  This paper introduces ChatTS, a novel MLLM designed for time series analysis.<n>ChatTS treats time series as a modality, similar to how vision MLLMs process images.<n>Time Series Evol-Instruct generates diverse time series Q&As, enhancing the model's reasoning capabilities.
  arXiv  Detail & Related papers  (2024-12-04T08:06:15Z)
• TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models [20.077169400691435]
  Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification.<n>LLMs directly encode embeddings for time series within the latent space of LLMs from scratch to align with semantic space of LLMs.<n>We propose TableTime, which reformulates MTSC as a table understanding task.
  arXiv  Detail & Related papers  (2024-11-24T07:02:32Z)
• Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification [4.5939667818289385]
  HiTime is a hierarchical multi-modal model that seamlessly integrates temporal information into large language models. Our findings highlight the potential of integrating temporal features into LLMs, paving the way for advanced time series analysis.
  arXiv  Detail & Related papers  (2024-10-24T12:32:19Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models [110.20279343734548]
  Time series forecasting holds significant importance in many real-world dynamic systems. We present Time-LLM, a reprogramming framework to repurpose large language models for time series forecasting. Time-LLM is a powerful time series learner that outperforms state-of-the-art, specialized forecasting models.
  arXiv  Detail & Related papers  (2023-10-03T01:31:25Z)
• Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning [101.66860222415512]
  Multi-Task Diffusion Model (textscMTDiff) is a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis. For generative planning, we find textscMTDiff outperforms state-of-the-art algorithms across 50 tasks on Meta-World and 8 maps on Maze2D.
  arXiv  Detail & Related papers  (2023-05-29T05:20:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.