FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series

TL;DR

FLAIRR-TS introduces a test-time prompt optimization framework for time series forecasting with LLMs, using agent-based iterative refinement and retrieval to improve accuracy without extensive tuning.

Contribution

It presents a novel agentic system for adaptive prompt refinement and retrieval, reducing the need for task-specific tuning in LLM-based time series forecasting.

Findings

Outperforms static prompting and retrieval baselines

Approaches the accuracy of specialized prompts

Demonstrates effectiveness across multiple benchmark datasets

Abstract

Time series Forecasting with large languagemodels (LLMs) requires bridging numericalpatterns and natural language. Effective fore-casting on LLM often relies on extensive pre-processing and fine-tuning.Recent studiesshow that a frozen LLM can rival specializedforecasters when supplied with a carefully en-gineered natural-language prompt, but craft-ing such a prompt for each task is itself oner-ous and ad-hoc. We introduce FLAIRR-TS, atest-time prompt optimization framework thatutilizes an agentic system: a Forecaster-agentgenerates forecasts using an initial prompt,which is then refined by a refiner agent, in-formed by past outputs and retrieved analogs.This adaptive prompting generalizes across do-mains using creative prompt templates andgenerates high-quality forecasts without inter-mediate code generation.Experiments onbenchmark datasets show improved accuracyover static prompting and retrieval-augmentedbaselines, approaching the performance ofspecialized prompts.FLAIRR-TS providesa practical alternative to tuning, achievingstrong performance via its agentic approach toadaptive prompt refinement and retrieval.