Year: 2026
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Liu, Jiashuo, Chen, Siyuan, Wang, Zaiyuan, Zeng, Zhiyuan, Guo, Jiacheng, Hu, Liang, Yin, Lingyue, Huang, Suozhi, Hao, Wenxin, Yang, Yang, Cheng, Zerui, Yao, Zixin, Yin, Lingyue, Liu, Haoxin, Cheng, Jiayi, Li, Yuzhen, Ma, Zezhong, Wang, Bingjie, Qiu, Bingsen, Liu, Xiao, Zhang, Zeyang, Liu, Zijian, Wang, Jinpeng, Yin, Mingren, He, Tianci, Liao, Yali, Tian, Yixiao, Zhu, Zhenwei, Dai, Anqi, Zhang, Ge, Liu, Jingkai, Zhang, Kaiyuan, Wu, Wenlong, Gao, Xiang, Chen, Xinjie, Yao, Zhixin, Wen, Zhoufutu, Prakash, B. Aditya, Blanchet, Jose, Wang, Mengdi, Si, Nian, Huang, Wenhao
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7125205457
Cites:
Cited by:
Related to: