FuguReport

MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters

Authors ChengAo Shen, Wenchao Yu, Fangyu Wu, Dongjin Song, Hanghang Tong, Dongsheng Luo, Wei Cheng, Haifeng Chen, Jingchao Ni
Affiliations University of Houston / University of Connecticut / Singapore Management University / University of Waterloo / NEC Labs / University of Illinois Urbana-Champaign
Categories Method / Multi-Agent Systems / Meta-harness optimized agent framework, Application / Time Series Forecasting / Few-shot forecasting for lightweight models, Task / Few-Shot Learning / Learning lightweight time series forecasters
License CC BY 4.0

Abstract Overview

This paper studies few-shot learning for lightweight time series forecasters, targeting resource-constrained settings where large foundation models are too costly and only small support sets are available. The proposed MetaCaster framework employs a multi-agent architecture in which a meta-generator produces domain-compliant synthetic training data from a few examples and textual context, a forecaster trainer trains and selects models from a 23-model lightweight library, and a meta-agent optimizes the generator's harness. Rather than producing forecasts directly through an LLM, the system acts as an intermediary engineer that prepares a compact specialist model for standalone deployment. Experiments on 18 datasets across in-domain and out-of-domain benchmarks evaluate MetaCaster against generative models, augmentation techniques, foundation models, and an agentic training pipeline.

Novelty

MetaCaster introduces an "agent-as-engineer" paradigm for time series forecasting, using agents to generate task-aligned training data and configure lightweight models rather than performing direct inference. It also introduces automatic meta-harness optimization that optimizes the generator's prompt and skill infrastructure based on downstream forecasting performance instead of pure data distribution matching.

Results

Across 30 dataset-and-shot evaluation settings, MetaCaster achieves the top MSE result in 19 cases and consistently outperforms established generative and augmentation baselines across shot sizes K in {10, 30, 50}. At K >= 30, forecasters trained on generated data frequently approach or exceed the performance of models trained on full authentic datasets, while generalizing effectively to out-of-domain benchmarks and held-out forecasters. On the Solar dataset, MetaCaster's selected lightweight forecaster attains performance comparable to time series foundation models with up to 10^3x lower latency and 10^5x fewer parameters.

Key Points

  1. MetaCaster aligns synthetic data generation directly with downstream forecasting error minimization rather than standard distributional realism metrics.
  2. The framework coordinates a Meta-Generator, a Forecaster Trainer managing the 23-model LT-Lib library, and a Harness Proposer that optimizes generator skills and prompts across training epochs.
  3. Ablation studies demonstrate that the forecasting-oriented objective and textual domain context are essential, while performance remains relatively stable across different LLM backbones, validating the centrality of harness optimization.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.