EMNLP Findings2025
FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
Gunjan Jalori, Preetika Verma, Sercan Ö. Arik
Abstract
Time series Forecasting with large language models (LLMs) requires bridging numerical patterns and natural language. Effective forecasting on LLM often relies on extensive preprocessing 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 highquality forecasts without intermediate code generation. Experiments on benchmark datasets show improved accuracy over static prompting and retrieval-augmented baselines, approaching the performance of specialized prompts. FLAIRR-TS provides a practical alternative to tuning, achieving strong performance via its agentic approach to adaptive prompt refinement and retrieval.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Are Transformers Effective for Time Series Forecasting? cites FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
- Are Transformers Effective for Time Series Forecasting? cites Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Cited by top-tier papers1
Builds on12
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series ForecastingHaoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang et al.AAAI 2021 · 7,289 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
- Are Transformers Effective for Time Series Forecasting?Ailing Zeng, Muxi Chen, Lei Zhang, Qiang XuAAAI 2023 · 3,619 citations
- FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series ForecastingTian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang et al.ICML 2022 · 2,912 citations
Related papers
- CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual LearningMinkyoung Kim, Daeun Ji, Yohan Lee, Beomsoo Kim et al.ACL Findings 2026
- LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term PromptingHaoxin Liu, Zhiyuan Zhao, Jindong Wang, Harshavardhan Kamarthi et al.ACL Findings 2024 · 33 citations
- From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with ReflectionXinlei Wang, Maike Feng, Jing Qiu, Jinjin Gu et al.NeurIPS 2024 · 181 citations
- Augur: Modeling Covariate Causal Associations in Time Series via Large Language ModelsZhiqing Cui, Binwu Wang, Qingxiang Liu, Yeqiang Wang et al.ACL 2026
- PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based SamplingYongchao Chen, Jacob Arkin, Yilun Hao, Yang Zhang et al.EMNLP 2024 · 6 citations
