{"ID":2878800,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19279","arxiv_id":"2508.19279","title":"FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series","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.","short_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 natur...","url_abs":"https://arxiv.org/abs/2508.19279","url_pdf":"https://arxiv.org/pdf/2508.19279v1","authors":"[\"Gunjan Jalori\",\"Preetika Verma\",\"Sercan Ö Arık\"]","published":"2025-08-24T00:57:22Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}