Agentic Retrieval-Augmented Generation for Time Series Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913481660301312 |
|---|---|
| author | Ravuru, Chidaksh Sakhinana, Sagar Srinivas Runkana, Venkataramana |
| author_facet | Ravuru, Chidaksh Sakhinana, Sagar Srinivas Runkana, Venkataramana |
| contents | Time series modeling is crucial for many applications, however, it faces challenges such as complex spatio-temporal dependencies and distribution shifts in learning from historical context to predict task-specific outcomes. To address these challenges, we propose a novel approach using an agentic Retrieval-Augmented Generation (RAG) framework for time series analysis. The framework leverages a hierarchical, multi-agent architecture where the master agent orchestrates specialized sub-agents and delegates the end-user request to the relevant sub-agent. The sub-agents utilize smaller, pre-trained language models (SLMs) customized for specific time series tasks through fine-tuning using instruction tuning and direct preference optimization, and retrieve relevant prompts from a shared repository of prompt pools containing distilled knowledge about historical patterns and trends to improve predictions on new data. Our proposed modular, multi-agent RAG approach offers flexibility and achieves state-of-the-art performance across major time series tasks by tackling complex challenges more effectively than task-specific customized methods across benchmark datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14484 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Agentic Retrieval-Augmented Generation for Time Series Analysis Ravuru, Chidaksh Sakhinana, Sagar Srinivas Runkana, Venkataramana Artificial Intelligence Computation and Language Machine Learning Time series modeling is crucial for many applications, however, it faces challenges such as complex spatio-temporal dependencies and distribution shifts in learning from historical context to predict task-specific outcomes. To address these challenges, we propose a novel approach using an agentic Retrieval-Augmented Generation (RAG) framework for time series analysis. The framework leverages a hierarchical, multi-agent architecture where the master agent orchestrates specialized sub-agents and delegates the end-user request to the relevant sub-agent. The sub-agents utilize smaller, pre-trained language models (SLMs) customized for specific time series tasks through fine-tuning using instruction tuning and direct preference optimization, and retrieve relevant prompts from a shared repository of prompt pools containing distilled knowledge about historical patterns and trends to improve predictions on new data. Our proposed modular, multi-agent RAG approach offers flexibility and achieves state-of-the-art performance across major time series tasks by tackling complex challenges more effectively than task-specific customized methods across benchmark datasets. |
| title | Agentic Retrieval-Augmented Generation for Time Series Analysis |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2408.14484 |