Visual Reasoning over Time Series via Multi-Agent System

TL;DR

MAS4TS is a multi-agent system that enhances visual reasoning and generalization in time series analysis by integrating structured priors, tool-driven coordination, and latent reconstruction, achieving state-of-the-art results.

Contribution

The paper introduces MAS4TS, a novel multi-agent framework that combines visual reasoning, tool selection, and latent reconstruction for versatile time series analysis.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Demonstrates strong generalization across diverse tasks.

Maintains efficient inference with multi-agent coordination.

Abstract

Time series analysis underpins many real-world applications, yet existing time-series-specific methods and pretrained large-model-based approaches remain limited in integrating intuitive visual reasoning and generalizing across tasks with adaptive tool usage. To address these limitations, we propose MAS4TS, a tool-driven multi-agent system for general time series tasks, built upon an Analyzer-Reasoner-Executor paradigm that integrates agent communication, visual reasoning, and latent reconstruction within a unified framework. MAS4TS first performs visual reasoning over time series plots with structured priors using a Vision-Language Model to extract temporal structures, and subsequently reconstructs predictive trajectories in latent space. Three specialized agents coordinate via shared memory and gated communication, while a router selects task-specific tool chains for execution. Extensive experiments on multiple benchmarks demonstrate that MAS4TS achieves state-of-the-art performance across a wide range of time series tasks, while exhibiting strong generalization and efficient inference.