arXiv cs.AI· Bokai Pan, Mingyue Cheng, Xiaoyu Tao, Zhiding Liu, Shuo Yu, Yuchong Wu, Qi Liu, Defu Lian, Enhong Chen·· 12 小时前AI 评分34
CastFlow：在智能体时间序列预测中打通证据获取与精准预测
CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting
AI 导读
CastFlow 是一个角色分工的智能体预测框架，用 Experience Memory 从训练数据中提炼成功工具调用轨迹，引导冻结的 LLM 调度多视角工具包获取证据，再由轻量专用 LLM 基于证据做时间推理以修正集成预测先验。该专用模型采用监督微调加可验证奖励强化学习的两阶段训练，以整体工作流的最终预测结果驱动优化。在十个真实基准上，CastFlow 于九个数据集优于竞争基线，代码已开源。
正文 · 原文
Abstract:Time series forecasting is a fundamental task in temporal data analytics, and large language model (LLM)-based agents offer a promising paradigm through autonomous tool interaction and evidence-grounded reasoning. However, two fundamental challenges remain: how to acquire forecast-relevant evidence through adaptive tool interactions, and how to translate such evidence into accurate numerical predictions. To address these challenges, we propose CastFlow, a role-specialized agentic forecasting framework that bridges general-purpose tool reasoning and specialized temporal forecasting. Specifically, CastFlow introduces an Experience Memory that distills successful tool-use trajectories from training data, guiding a frozen LLM to orchestrate a multi-view toolkit for evidence acquisition. A lightweight specialized LLM then performs evidence-grounded temporal reasoning to refine an ensemble forecasting prior. To enhance this capability, we develop a two-stage training strategy combining supervised fine-tuning and reinforcement learning with verifiable rewards, where final forecasting outcomes of the overall workflow guide the optimization of the specialized model. Extensive experiments on ten real-world benchmarks demonstrate that CastFlow outperforms competitive baselines on nine datasets. Our findings highlight the importance of bridging autonomous evidence acquisition and specialized temporal reasoning for accurate and adaptive agentic forecasting. The source code is available at this https URL.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.27840 [cs.LG] |
| (or arXiv:2604.27840v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.27840 arXiv-issued DOI via DataCite |
Submission history
From: Bokai Pan [view email]
[v1]
Thu, 30 Apr 2026 13:24:42 UTC (15,646 KB)
[v2]
Mon, 4 May 2026 08:56:40 UTC (15,648 KB)
[v3]
Fri, 16 Oct 2026 03:01:02 UTC (2,174 KB)
来源：arXiv cs.AI · arxiv.org