发表机构
University of Maryland, College Park; University of Illinois Urbana-Champaign; University of Illinois Chicago; MBZUAI（马里兰大学帕克分校; 伊利诺伊大学厄巴纳-香槟分校; 伊利诺伊大学芝加哥分校; Mohamed Bin Zayed University of Artificial Intelligence）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对时间序列推理中不同模型能力互补及特性差异问题，提出基于图的TSRouter动态路由框架，通过构建异构图并将路由设为候选评分问题来选择最优模态-模型对，在多任务评估中性能显著提升，还具备零样本泛化等优势。
AI 中文摘要
时间序列推理对解决现实世界问题至关重要。大语言模型（LLMs）和视觉-语言模型（VLMs）在处理时间序列数据时能力互补。LLMs将时间序列作为文本序列处理，保留精确数值理解，但难以处理全局模式；VLMs通过可视化时间序列有效捕捉模式，但可能丢失细粒度细节。此外，模型在特定任务专业知识和推理成本上差异显著。为此，引入TSRouter，一个基于图的动态路由框架。它构建任务、查询、模态和模型节点的异构图来关联查询特征、模态属性和模型能力。将路由制定为候选评分问题，根据用户定义的性能-成本偏好评估每个模态-模型对以选择最优候选。在4个不同时间序列推理任务上的综合评估表明，TSRouter显著优于各种基线，相对提升16%至46%。此外，TSRouter展示了对未见模型和新任务的强大零样本即插即用泛化能力，并通过成本感知优化在降低计算开销的同时保持高性能。
英文摘要
Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, their capabilities are complementary: LLMs process time series as text sequences and thus preserve exact numerical understanding, but struggle with global patterns, whereas VLMs efficiently capture these patterns by visualizing time series but may lose fine-grained details. Moreover, models vary significantly in task-specific expertise and inference costs. Dynamically selecting the most suitable modality and model for each query is therefore crucial, yet challenging because it requires modeling the complex interactions among tasks, queries, modalities, and models, which carry rich contextual signals. To this end, we introduce TSRouter, a graph-based dynamic routing framework. TSRouter constructs a heterogeneous graph of task, query, modality, and model nodes to contextualize the interactions among query characteristics, modality attributes, and model capabilities. TSRouter formulates routing as a candidate scoring problem, where each modality-model pair is evaluated based on user-defined performance-cost preferences to select the optimal candidate. Comprehensive evaluations on 4 distinct time series reasoning tasks reveal that TSRouter substantially outperforms diverse baselines with 16\% to 46\% relative improvements. Furthermore, TSRouter demonstrates robust zero-shot plug-and-play generalization to unseen models and novel tasks and preserves high performance while reducing computational overhead through cost-aware optimization. Our code is available at https://github.com/tianyi-lab/TSRouter.
CommentsAccepted to COLM 2026
