用少量数据训练轻量时序预测模型，让代理自动造出专用预测器。
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
- 代理生成数据，自动训练轻量预测模型
- 仅需少量样本即可达到高精度预测
- 适合数据少、算力低的场景使用
时序预测正朝多模态与智能体化方向发展，但在资源受限场景中使用基础模型成本过高，更需轻量级专用预测模型。然而轻量模型通常需要大量训练数据，限制了在数据稀缺、缓慢积累或隐私敏感领域的应用。为此，我们研究了轻量预测模型的少样本学习问题。提出 MetaCaster：一种元引导优化的多智能体框架，通过智能体生成数据，仅凭少数样本与文本上下文即可自动训练出专用轻量预测模型。本工作揭示了一种新范式：智能体不直接做预测，而是作为中间工程师，构建高效、任务特定的预测器用于部署。在18个数据集、23种先进轻量预测模型和14个基线上的实验表明，MetaCaster在保证高质量预测性能的同时，兼具数据效率与计算效率。
原文摘要 · Abstract (English)
Time series forecasting (TSF) is evolving toward multimodal and agentic settings, yet using foundation models remains uneconomical in resource-constrained scenarios, where compact, specialized forecasters are more desirable. However, lightweight forecasters typically require substantial training data, limiting their use in domains with scarce, slowly accumulated, or privacy-sensitive time series. To address this dilemma, we investigate the challenging problem of few-shot learning for lightweight forecasters. We propose MetaCaster, a meta-harness-optimized multi-agent framework that uses agentic data generation to automatically train specialized lightweight forecasters from only a few examples and textual contexts. Our work highlights a new TSF paradigm in which agents act not as forecasters but as intermediary engineers that prepare efficient, task-specific forecasters for deployment. Experiments on 18 datasets, 23 state-of-the-art lightweight forecasters, and 14 baselines demonstrate that MetaCaster achieves both data efficiency and computational efficiency while maintaining high-quality TSF performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。