Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation

TL;DR

This paper critically examines the current state of time series reasoning with multimodal large language models, highlighting key gaps in model design, task formulation, and evaluation, and advocates for a unified approach to improve robustness, interpretability, and decision relevance.

Contribution

The paper provides a comprehensive analysis of recent works, identifies critical gaps, and proposes a new perspective emphasizing the need for integrated model design, task formulation, and evaluation strategies.

Findings

Existing methods adapt NLP techniques with limited focus on time series properties.

Current tasks are mostly traditional prediction and classification.

Evaluations prioritize benchmarks over robustness and interpretability.

Abstract

Understanding time series data is fundamental to many real-world applications. Recent work explores multimodal large language models (MLLMs) to enhance time series understanding with contextual information beyond numerical signals. This area has grown from 7 papers in 2023 to over 580 in 2025, yet existing methods struggle in real-world settings. We analyze 20 influential works from 2025 across model design, task formulation, and evaluation, and identify critical gaps: methods adapt NLP techniques with limited attention to core time series properties; tasks remain restricted to traditional prediction and classification; and evaluations emphasize benchmarks over robustness, interpretability, or decision relevance. We argue that achieving time series reasoning requires rethinking model design, task formulation, and evaluation together. We define time series reasoning, outline challenges and future directions, and call on researchers to develop unified frameworks for robust, interpretable, and decision-relevant reasoning in real-world applications. The material is available at https://github.com/Eleanorkong/Awesome-Time-Series-Reasoning.