Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation

Publication Date: 3/29/2026

Event: The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026)

Reference: pp. 1-38, 2026

Authors: Minhua Lin, The Pennsylvania State University; Zhengzhang Chen, NEC Laboratories America, Inc.; Yanchi Liu, NEC Laboratories America, Inc.; Xujiang Zhao, NEC Laboratories America, Inc.; Zongyu Wu, The Pennsylvania State University; Junxiang Wang, NEC Laboratories America, Inc.; Xiang Zhang, The Pennsylvania State University; Suhang Wang, The Pennsylvania State University; Haifeng Chen, NEC Laboratories America, Inc.

Abstract: Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time series and facilitating downstream tasks. However, obtaining such annotations is challenging, particularly in mission-critical domains. In this paper, we propose TESSA, a multi-agent system designed to automatically generate both general and domain-specific annotations for time series data. TESSA introduces two agents: a general annotation agent and a domain-specific annotation agent. The general agent captures common patterns and knowledge across multiple source domains, leveraging both time-series-wise and text-wise features to generate general annotations. Meanwhile, the domain-specific agent utilizes limited annotations from the target domain to learn domain-specific terminology and generate targeted annotations. Extensive experiments on multiple synthetic and real-world datasets demonstrate that TESSA effectively generates high-quality annotations, outperforming existing methods.

Publication Link: