FutureX-Pro：将未来预测拓展至高价值垂直领域
人工智能
2026-01-21 v1 计算工程、金融与科学
机器学习
摘要
在建立通用未来预测实时基准的 FutureX 基础上，本报告介绍了 FutureX-Pro，包括 FutureX-Finance、FutureX-Retail、FutureX-PublicHealth、FutureX-NaturalDisaster 和 FutureX-Search。它们共同构成了一个将智能体未来预测拓展至高价值垂直领域的专用框架。尽管通用智能体在开放域搜索中表现出色，但它们在资本密集型和安全性关键领域的可靠性仍未得到充分探索。FutureX-Pro 瞄准四个具有经济和社会重要性的垂直领域：金融、零售、公共卫生和自然灾害。我们对智能体大语言模型（LLMs）在入门级但基础性的预测任务上进行基准测试——从预测市场指标和供应链需求，到追踪流行病趋势和自然灾害。通过采用 FutureX 的无污染、实时评估流程，我们评估了当前最先进的（SOTA）智能体大语言模型是否具备工业部署所需的领域基础。我们的发现揭示了通用推理与高价值垂直应用所需精度之间的性能差距。
引用
@article{arxiv.2601.12259,
title = {FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains},
author = {Jiashuo Liu and Siyuan Chen and Zaiyuan Wang and Zhiyuan Zeng and Jiacheng Guo and Liang Hu and Lingyue Yin and Suozhi Huang and Wenxin Hao and Yang Yang and Zerui Cheng and Zixin Yao and Lingyue Yin and Haoxin Liu and Jiayi Cheng and Yuzhen Li and Zezhong Ma and Bingjie Wang and Bingsen Qiu and Xiao Liu and Zeyang Zhang and Zijian Liu and Jinpeng Wang and Mingren Yin and Tianci He and Yali Liao and Yixiao Tian and Zhenwei Zhu and Anqi Dai and Ge Zhang and Jingkai Liu and Kaiyuan Zhang and Wenlong Wu and Xiang Gao and Xinjie Chen and Zhixin Yao and Zhoufutu Wen and B. Aditya Prakash and Jose Blanchet and Mengdi Wang and Nian Si and Wenhao Huang},
journal= {arXiv preprint arXiv:2601.12259},
year = {2026}
}
备注
21 pages