mlsanityData to 14 Oct 2026

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

arXiv 2508.19279 ↗First posted 24 Aug 2025cs.CL cs.AIcited by 6

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 9 of its 20 references that are in the map. First posted on arXiv 24 Aug 2025.

Builds on

9 of 20 references.

References · 9

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  5. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  7. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  8. 2024LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Promptingcited by 59
  9. 2023Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter Viewcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoningcited by 5
  2. 2026Bridging the Last Mile of Time Series Forecasting with LLM Agentscited by 3
  3. 2026TimeClaw: A Time-Series AI Agent with Exploratory Execution Learningcited by 2
  4. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applicationscited by 1
  5. 2026LLM Agents for Time-Series: A Surveycited by 1
  6. 2026MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasterscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Context information can be more important than reasoning for time series forecasting with a large language model
  2. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
  3. 2026CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning
  4. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  5. 2025STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
  6. 2025Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs
  7. 2026Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs
  8. 2026OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning