Agentic Retrieval-Augmented Generation for Time Series Analysis
This addresses time series analysis problems for applications requiring accurate predictions, but it appears incremental as it builds on existing RAG and multi-agent concepts.
The paper tackles challenges in time series modeling like spatio-temporal dependencies and distribution shifts by proposing an agentic Retrieval-Augmented Generation framework with a hierarchical multi-agent architecture, achieving state-of-the-art performance across major benchmark datasets.
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.