TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models

• URL: http://arxiv.org/abs/2609.13457v1
• Date: Fri, 11 Sep 2026 19:22:05 GMT
• Title: TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models
• Abstract summary: We present TimeThink, a synthetic framework for eliciting compositional timeseries reasoning.<n>TimeThink first designs a synthetic data generator that produces atomic and composite question-answer pairs.<n>Unlike template-reliant methods, this approach enables the model to learn the underlying logic of composition rather than simply imitating traces.
• Score: 6.191461643266362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Timeseries multimodal large language models (TS-MLLMs) have recently begun leveraging the reasoning capabilities of large language models (LLMs) for question-answering tasks. However, these models often fail to capture dynamic temporal patterns, providing only implicit reasoning that lacks the underlying explanations critical for high-stakes applications like healthcare. While reinforcement learning (RL)-based timeseries language models aim to address this, they often fall short because they are trained on narrow, in-distribution data and struggle with out-of-distribution compositional questions. To address these challenges, we present TimeThink, a synthetic framework for eliciting compositional timeseries reasoning. Core timeseries primitives (e.g., trend, seasonality) are domain-independent and can be deterministically generated. Guided by this premise, TimeThink first designs a synthetic data generator that produces atomic and composite question-answer pairs, providing objective ground truth with reasoning traces. Building on this framework, TimeThink employs a reinforcement learning with verifiable rewards (RLVR) training strategy that encourages explicit reasoning. Unlike template-reliant methods, this approach enables the model to learn the underlying logic of composition rather than simply imitating traces. Extensive experiments show that TimeThink, trained only on synthetic data, significantly outperforms strong baselines on both synthetic and real-world benchmarks.

Related papers

• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling [85.590774707406]
  Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs.<n>We introduce UniT, a framework for multimodal test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds.
  arXiv  Detail & Related papers  (2026-02-12T18:59:49Z)
• Reasoning Pattern Alignment Merging for Adaptive Reasoning [48.347817456299104]
  Reasoning Pattern Alignment Merging (RPAM)<n>RPAM is a layer-wise model merging framework based on feature alignment to facilitate query-adaptive reasoning.<n> Experiments on seven widely used reasoning benchmarks show that RPAM substantially reduces inference cost while maintaining strong performance.
  arXiv  Detail & Related papers  (2026-01-07T01:36:39Z)
• Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models [39.75347938309383]
  We propose the rationale-grounded in-context learning for time series reasoning, where rationales work as guiding reasoning units rather than post-hoc explanations.<n>We conduct extensive experiments to demonstrate the effectiveness and efficiency of our proposed RationaleTS on three-domain time series reasoning tasks.
  arXiv  Detail & Related papers  (2026-01-06T12:27:04Z)
• TimeSense:Making Large Language Models Proficient in Time-Series Analysis [26.44226032396234]
  In the time-series domain, an increasing number of works combine text with temporal data to leverage the reasoning capabilities of large language models.<n>We propose TimeSense, a framework that makes LLMs proficient in time-series analysis by balancing textual reasoning with a preserved temporal sense.<n>TimeSense achieves state-of-the-art performance across multiple tasks, and it particularly outperforms existing methods on complex multi-dimensional time-series reasoning tasks.
  arXiv  Detail & Related papers  (2025-11-09T12:00:18Z)
• Understanding the Implicit Biases of Design Choices for Time Series Foundation Models [90.894232610821]
  Time series foundation models (TSFMs) are a class of potentially powerful, general-purpose tools for time series forecasting and related temporal tasks.<n>Their behavior is strongly shaped by subtle inductive biases in their design.<n>We show how these biases can be intuitive or very counterintuitive, depending on properties of the model and data.
  arXiv  Detail & Related papers  (2025-10-22T04:42:35Z)
• Can an LLM Induce a Graph? Investigating Memory Drift and Context Length [11.214847796972705]
  Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs)<n>We argue for evaluating these models on more complex reasoning tasks that require them to induce structured relational knowledge from the text.<n>Our findings reveal that LLMs begin to exhibit memory drift and contextual forgetting at much shorter effective lengths when tasked with this form of relational reasoning.
  arXiv  Detail & Related papers  (2025-10-04T01:56:07Z)
• Towards Interpretable Time Series Foundation Models [0.0]
  We generate natural language annotations using a large multimodal model and use these to supervise the fine-tuning of compact Qwen models.<n>Our results highlight the feasibility of compressing time series understanding into lightweight, language-capable models suitable for on-device or privacy-sensitive deployment.
  arXiv  Detail & Related papers  (2025-07-10T05:29:34Z)
• Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models [21.579319926212296]
  Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks.<n>They struggle with temporal reasoning, which requires processing time-related information such as event sequencing, durations, and inter-temporal relationships.<n>We introduce TISER, a novel framework that enhances the temporal reasoning abilities of LLMs through a multi-stage process that combines timeline construction with iterative self-reflection.
  arXiv  Detail & Related papers  (2025-04-07T16:51:45Z)
• Large Language Models Can Learn Temporal Reasoning [11.599570446840547]
  We propose TG-LLM, a novel framework towards language-based temporal reasoning. Instead of reasoning over the original context, we adopt a latent representation, temporal graph (TG) A synthetic dataset (TGQA) is fully controllable and requires minimal supervision.
  arXiv  Detail & Related papers  (2024-01-12T19:00:26Z)
• 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)
• TRAM: Benchmarking Temporal Reasoning for Large Language Models [12.112914393948415]
  We introduce TRAM, a temporal reasoning benchmark composed of ten datasets. We evaluate popular language models like GPT-4 and Llama2 in zero-shot and few-shot scenarios. Our findings indicate that the best-performing model lags significantly behind human performance.
  arXiv  Detail & Related papers  (2023-10-02T00:59:07Z)
• Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic [84.59255070520673]
  Large language models (LLMs) face a challenge when engaging in temporal reasoning. We propose TempLogic, a novel framework designed specifically for temporal question-answering tasks.
  arXiv  Detail & Related papers  (2023-05-24T10:57:53Z)
• Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings [61.04460792203266]
  We introduce VCoT, a novel method that leverages chain-of-thought prompting with vision-language grounding to bridge the logical gaps within sequential data. Our method uses visual guidance to generate synthetic multimodal infillings that add consistent and novel information to reduce the logical gaps for downstream tasks.
  arXiv  Detail & Related papers  (2023-05-03T17:58:29Z)

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.