Model-agnostic Retrieval-Augmented Extended Forecasting for time series

• 类型：arxiv
• 标识：2608.14054
• 链接：http://arxiv.org/abs/2608.14054v1
• 主分类：rag
• 形态：application
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：Empirical evaluation across multiple benchmark datasets demonstrates that RAEF outperforms RAF in both accuracy and inference overhead, and comprehensive comparisons with zero-shot and fine-tuned foundation models show that RAEF achieves competitive or superior performance to fine-tuning while avoiding its computational burden.
• 副分类：engineering
• 待LLM分类：否
• 标题中文：模型无关的检索增强扩展时间序列预测
• TLDR中文：在多个 benchmark 数据集上的实证评估表明，RAEF 在准确率和推理开销方面均优于 RAF，并且与零样本及微调基础模型的全面对比显示，RAEF 在避免微计算负担的同时取得了与微调相当或更优的性能。
• 来源文件：
• /inbox/tom/_candidates/2026-08-18-agent-rag-longcontext-candidates.json
• [S2 enrich]