FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
This work addresses the challenge of ad-hoc prompt engineering for time series forecasting with LLMs, offering a practical alternative to tuning, though it appears incremental as it builds on existing prompting and retrieval methods.
The paper tackles the problem of time series forecasting with large language models by introducing FLAIRR-TS, a test-time prompt optimization framework that uses an agentic system for iterative refinement and retrieval, resulting in improved accuracy over static prompting and retrieval-augmented baselines, approaching specialized prompt performance.
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.