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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jalori, Gunjan, Verma, Preetika, Arık, Sercan Ö
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908505160548352
author Jalori, Gunjan
Verma, Preetika
Arık, Sercan Ö
author_facet Jalori, Gunjan
Verma, Preetika
Arık, Sercan Ö
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
Jalori, Gunjan
Verma, Preetika
Arık, Sercan Ö
Computation and Language
Artificial Intelligence
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.
title FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.19279