@inproceedings{jalori-etal-2025-flairr,
title = "{FLAIRR}-{TS} - Forecasting {LLM}-Agents with Iterative Refinement and Retrieval for Time Series",
author = "Jalori, Gunjan and
Verma, Preetika and
Arik, Sercan O",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.834/",
doi = "10.18653/v1/2025.findings-emnlp.834",
pages = "15427--15437",
ISBN = "979-8-89176-335-7",
abstract = "Time series Forecasting with large language models (LLMs) requires bridging numerical patterns and natural language. Effective forecasting on LLM often relies on extensive pre-processing and fine-tuning. Recent studies show that a frozen LLM can rival specialized forecasters when supplied with a carefully engineered natural-language prompt, but crafting such a prompt for each task is itself onerous and ad-hoc. We introduce FLAIRR-TS, a test-time prompt optimization framework that utilizes an agentic system: a Forecaster-agent generates forecasts using an initial prompt, which is then refined by a refiner agent, informed by past outputs and retrieved analogs. This adaptive prompting generalizes across domains using creative prompt templates and generates high-quality forecasts without intermediate code generation. Experiments on benchmark datasets show FLAIRR-TS improves forecasting over static prompting and retrieval-augmented baselines, approaching the performance of specialized prompts.FLAIRR-TS provides a practical alternative to fine-tuning, achieving strong performance via its agentic approach to adaptive prompt refinement and retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jalori-etal-2025-flairr">
<titleInfo>
<title>FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gunjan</namePart>
<namePart type="family">Jalori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preetika</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sercan</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Arik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Time series Forecasting with large language models (LLMs) requires bridging numerical patterns and natural language. Effective forecasting on LLM often relies on extensive pre-processing and fine-tuning. Recent studies show that a frozen LLM can rival specialized forecasters when supplied with a carefully engineered natural-language prompt, but crafting such a prompt for each task is itself onerous and ad-hoc. We introduce FLAIRR-TS, a test-time prompt optimization framework that utilizes an agentic system: a Forecaster-agent generates forecasts using an initial prompt, which is then refined by a refiner agent, informed by past outputs and retrieved analogs. This adaptive prompting generalizes across domains using creative prompt templates and generates high-quality forecasts without intermediate code generation. Experiments on benchmark datasets show FLAIRR-TS improves forecasting over static prompting and retrieval-augmented baselines, approaching the performance of specialized prompts.FLAIRR-TS provides a practical alternative to fine-tuning, achieving strong performance via its agentic approach to adaptive prompt refinement and retrieval.</abstract>
<identifier type="citekey">jalori-etal-2025-flairr</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.834</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.834/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15427</start>
<end>15437</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
%A Jalori, Gunjan
%A Verma, Preetika
%A Arik, Sercan O.
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F jalori-etal-2025-flairr
%X Time series Forecasting with large language models (LLMs) requires bridging numerical patterns and natural language. Effective forecasting on LLM often relies on extensive pre-processing and fine-tuning. Recent studies show that a frozen LLM can rival specialized forecasters when supplied with a carefully engineered natural-language prompt, but crafting such a prompt for each task is itself onerous and ad-hoc. We introduce FLAIRR-TS, a test-time prompt optimization framework that utilizes an agentic system: a Forecaster-agent generates forecasts using an initial prompt, which is then refined by a refiner agent, informed by past outputs and retrieved analogs. This adaptive prompting generalizes across domains using creative prompt templates and generates high-quality forecasts without intermediate code generation. Experiments on benchmark datasets show FLAIRR-TS improves forecasting over static prompting and retrieval-augmented baselines, approaching the performance of specialized prompts.FLAIRR-TS provides a practical alternative to fine-tuning, achieving strong performance via its agentic approach to adaptive prompt refinement and retrieval.
%R 10.18653/v1/2025.findings-emnlp.834
%U https://aclanthology.org/2025.findings-emnlp.834/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.834
%P 15427-15437
Markdown (Informal)
[FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series](https://aclanthology.org/2025.findings-emnlp.834/) (Jalori et al., Findings 2025)
ACL