AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xiaohan, Gao, Tian, Cheng, Mingyue, Pan, Bokai, Guo, Ze, Liu, Yaguo, Tao, Xiaoyu, Liu, Qi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911579226767360
author Zhang, Xiaohan
Gao, Tian
Cheng, Mingyue
Pan, Bokai
Guo, Ze
Liu, Yaguo
Tao, Xiaoyu
Liu, Qi
author_facet Zhang, Xiaohan
Gao, Tian
Cheng, Mingyue
Pan, Bokai
Guo, Ze
Liu, Yaguo
Tao, Xiaoyu
Liu, Qi
contents Time series forecasting plays a crucial role in decision-making across many real-world applications. Despite substantial progress, most existing methods still treat forecasting as a static, single-pass regression problem. In contrast, human experts form predictions through iterative reasoning that integrates temporal features, domain knowledge, case-based references, and supplementary context, with continuous refinement. In this work, we propose Alphacast, an interaction-driven agentic reasoning framework that enables accurate time series forecasting with training-free large language models. Alphacast reformulates forecasting as an expert-like process and organizes it into a multi-stage workflow involving context preparation, reasoning-based generation, and reflective evaluation, transforming forecasting from a single-pass output into a multi-turn, autonomous interaction process. To support diverse perspectives commonly considered by human experts, we develop a lightweight toolkit comprising a feature set, a knowledge base, a case library, and a contextual pool that provides external support for LLM-based reasoning. Extensive experiments across multiple benchmarks show that Alphacast generally outperforms representative baselines. Code is available at this repository: https://github.com/echo01-ai/AlphaCast.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08947
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting
Zhang, Xiaohan
Gao, Tian
Cheng, Mingyue
Pan, Bokai
Guo, Ze
Liu, Yaguo
Tao, Xiaoyu
Liu, Qi
Artificial Intelligence
Time series forecasting plays a crucial role in decision-making across many real-world applications. Despite substantial progress, most existing methods still treat forecasting as a static, single-pass regression problem. In contrast, human experts form predictions through iterative reasoning that integrates temporal features, domain knowledge, case-based references, and supplementary context, with continuous refinement. In this work, we propose Alphacast, an interaction-driven agentic reasoning framework that enables accurate time series forecasting with training-free large language models. Alphacast reformulates forecasting as an expert-like process and organizes it into a multi-stage workflow involving context preparation, reasoning-based generation, and reflective evaluation, transforming forecasting from a single-pass output into a multi-turn, autonomous interaction process. To support diverse perspectives commonly considered by human experts, we develop a lightweight toolkit comprising a feature set, a knowledge base, a case library, and a contextual pool that provides external support for LLM-based reasoning. Extensive experiments across multiple benchmarks show that Alphacast generally outperforms representative baselines. Code is available at this repository: https://github.com/echo01-ai/AlphaCast.
title AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting
topic Artificial Intelligence
url https://arxiv.org/abs/2511.08947