FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains
Jiashuo Liu, Siyuan Chen, Zaiyuan Wang, Zhiyuan Zeng, Jiacheng Guo, Liang Hu, Lingyue Yin, Suozhi Huang, Wenxin Hao, Yang Yang, Zerui Cheng, Zixin Yao, Lingyue Yin, Haoxin Liu, Jiayi Cheng, Yuzhen Li, Zezhong Ma, Bingjie Wang, Bingsen Qiu, Xiao Liu, Zeyang Zhang, Zijian Liu, Jinpeng Wang, Mingren Yin, Tianci He, Yali Liao, Yixiao Tian, Zhenwei Zhu, Anqi Dai, Ge Zhang, Jingkai Liu, Kaiyuan Zhang, Wenlong Wu, Xiang Gao, Xinjie Chen, Zhixin Yao, Zhoufutu Wen, B. Aditya Prakash, Jose Blanchet, Mengdi Wang, Nian Si, Wenhao Huang
TL;DR
FutureX-Pro targets the challenge of grounding AI future-prediction in high-value vertical domains by introducing domain-specific benchmarks (FutureX-Finance, FutureX-Retail, FutureX-PublicHealth, FutureX-NaturalDisaster) and a retrieval-oriented FutureX-Search track. It leverages a contamination-free live evaluation pipeline to assess whether current SOTA agentic LLMs possess the domain grounding for industrial deployment, revealing a persistent gap between generalist reasoning and the precision required for such settings. The framework emphasizes rigorous data provenance, source authority, and probabilistic forecasting, highlighting the need for deep-domain grounding, robust retrieval strategies, and uncertainty calibration. Overall, FutureX-Pro provides a multi-vertical stress test that informs deployment-readiness and charts future directions for domain-aware, safe, and reliable AI assistants in finance, retail, public health, and disaster risk domains.
Abstract
Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, FutureX-PublicHealth, FutureX-NaturalDisaster, and FutureX-Search. These together form a specialized framework extending agentic future prediction to high-value vertical domains. While generalist agents demonstrate proficiency in open-domain search, their reliability in capital-intensive and safety-critical sectors remains under-explored. FutureX-Pro targets four economically and socially pivotal verticals: Finance, Retail, Public Health, and Natural Disaster. We benchmark agentic Large Language Models (LLMs) on entry-level yet foundational prediction tasks -- ranging from forecasting market indicators and supply chain demands to tracking epidemic trends and natural disasters. By adapting the contamination-free, live-evaluation pipeline of FutureX, we assess whether current State-of-the-Art (SOTA) agentic LLMs possess the domain grounding necessary for industrial deployment. Our findings reveal the performance gap between generalist reasoning and the precision required for high-value vertical applications.