LLM as Forecasting Planner framework integrates LLMs with TSFMs for improved forecasting

Researchers have developed a novel framework called LLM as Forecasting Planner (LAFP) that integrates large language models (LLMs) with time-series foundation models (TSFMs) for improved forecasting. This training-free approach uses an LLM to guide the planning process over TSFM-generated trajectories, acting as a policy and value function. Experiments on benchmark datasets demonstrated that LAFP consistently enhances forecasting accuracy across various TSFM and LLM combinations. AI

IMPACT This framework offers a training-free method to enhance time-series forecasting by leveraging LLMs with existing foundation models, potentially improving accuracy in contexts requiring both numerical and textual data.

RANK_REASON The cluster contains an academic paper detailing a new methodology for time-series forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Chronos
• Judge
• LLM as Forecasting Planner
• Monte Carlo tree search
• Ranker
• Time-MMD
• TimesFM

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →