Visual Reasoning over Time Series via Multi-Agent System
This addresses limitations in time series analysis for real-world applications by enabling more flexible and generalizable task handling, though it appears incremental as it builds on existing paradigms like multi-agent systems and vision-language models.
The paper tackles the problem of integrating intuitive visual reasoning and adaptive tool usage in time series analysis by proposing MAS4TS, a multi-agent system that achieves state-of-the-art performance across multiple benchmarks with strong generalization and efficient inference.
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.