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

arXiv: https://arxiv.org/abs/2410.17462 · HTML: https://mlsanity.com/paper/2410.17462/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 22 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters](https://mlsanity.com/paper/2308.08469/) (2023)
- [Voice2Series: Reprogramming Acoustic Models for Time Series Classification](https://mlsanity.com/paper/2106.09296/) (2021)
- [A Survey of Large Language Models in Finance (FinLLMs)](https://mlsanity.com/paper/2402.02315/) (2024)
- [PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains](https://mlsanity.com/paper/2102.12206/) (2021)
- [Empowering Time Series Analysis with Large Language Models: A Survey](https://mlsanity.com/paper/2402.03182/) (2024)
- [LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning](https://mlsanity.com/paper/2406.01032/) (2024)
- [UDApter -- Efficient Domain Adaptation Using Adapters](https://mlsanity.com/paper/2302.03194/) (2023)

## Built on by (most cited first, 21 of 21)

- [Multi-modal Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2503.13709/) (2025)
- [A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications](https://mlsanity.com/paper/2510.16724/) (2025)
- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [Position: Agentic Evolution is the Path to Evolving LLMs](https://mlsanity.com/paper/2602.00359/) (2026)
- [Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network](https://mlsanity.com/paper/2412.15678/) (2024)
- [Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models](https://mlsanity.com/paper/2503.11411/) (2025)
- [LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models](https://mlsanity.com/paper/2502.12359/) (2025)
- [Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights](https://mlsanity.com/paper/2503.01895/) (2025)
- [MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution](https://mlsanity.com/paper/2603.18718/) (2026)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework](https://mlsanity.com/paper/2507.21830/) (2025)
- [CrowdAgent: Multi-Agent Managed Multi-Source Annotation System](https://mlsanity.com/paper/2509.14030/) (2025)
- [Reasoning on Time-Series for Financial Technical Analysis](https://mlsanity.com/paper/2511.08616/) (2025)
- [How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities](https://mlsanity.com/paper/2502.18387/) (2025)
- [AXIS: Explainable Time Series Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2509.24378/) (2025)
- [Stealing Training Graphs from Graph Neural Networks](https://mlsanity.com/paper/2411.11197/) (2024)
- [Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models](https://mlsanity.com/paper/2506.12340/) (2025)
- [Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision](https://mlsanity.com/paper/2510.16980/) (2025)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion](https://mlsanity.com/paper/2510.20651/) (2025)
- [LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification](https://mlsanity.com/paper/2610.01800/) (2026)

## Abstract (arXiv)

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.