The Innovation (Jun 2025)
Foundation models and intelligent decision-making: Progress, challenges, and perspectives
- Jincai Huang,
- Yongjun Xu,
- Qi Wang,
- Qi (Cheems) Wang,
- Xingxing Liang,
- Fei Wang,
- Zhao Zhang,
- Wei Wei,
- Boxuan Zhang,
- Libo Huang,
- Jingru Chang,
- Liantao Ma,
- Ting Ma,
- Yuxuan Liang,
- Jie Zhang,
- Jian Guo,
- Xuhui Jiang,
- Xinxin Fan,
- Zhulin An,
- Tingting Li,
- Xuefei Li,
- Zezhi Shao,
- Tangwen Qian,
- Tao Sun,
- Boyu Diao,
- Chuanguang Yang,
- Chenqing Yu,
- Yiqing Wu,
- Mengxian Li,
- Haifeng Zhang,
- Yongcheng Zeng,
- Zhicheng Zhang,
- Zhengqiu Zhu,
- Yiqin Lv,
- Aming Li,
- Xu Chen,
- Bo An,
- Wei Xiao,
- Chenguang Bai,
- Yuxing Mao,
- Zhigang Yin,
- Sheng Gui,
- Wentao Su,
- Yinghao Zhu,
- Junyi Gao,
- Xinyu He,
- Yizhou Li,
- Guangyin Jin,
- Xiang Ao,
- Xuehao Zhai,
- Haoran Tan,
- Lijun Yun,
- Hongquan Shi,
- Jun Li,
- Changjun Fan,
- Kuihua Huang,
- Ewen Harrison,
- Victor C.M. Leung,
- Sihang Qiu,
- Yanjie Dong,
- Xiaolong Zheng,
- Gang Wang,
- Yu Zheng,
- Yuanzhuo Wang,
- Jiafeng Guo,
- Lizhe Wang,
- Xueqi Cheng,
- Yaonan Wang,
- Shanlin Yang,
- Mengyin Fu,
- Aiguo Fei
Affiliations
- Jincai Huang
- College of Systems Engineering, National University of Defense Technology, Changsha 410073, China; Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China
- Yongjun Xu
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Qi Wang
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Qi (Cheems) Wang
- Department of Automation, Tsinghua University, Beijing 100084, China
- Xingxing Liang
- Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China
- Fei Wang
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Zhao Zhang
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Wei Wei
- Huazhong University of Science and Technology, Wuhan 430074, China
- Boxuan Zhang
- School of Automation, Beijing Institute of Technology, Beijing 100081, China
- Libo Huang
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Jingru Chang
- School of Information Science and Engineering, Dalian Polytechnic University, Dalian 116034, China
- Liantao Ma
- National Engineering Research Center for Software Engineering, Peking University, Beijing 100871, China
- Ting Ma
- Department of Oral Implantology, Peking University School and Hospital of Stomatology, Beijing 100081, China
- Yuxuan Liang
- The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China
- Jie Zhang
- College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China; State Key Laboratory of Efficient Utilization of Agricultural Water Resources, Beijing 100083, China
- Jian Guo
- IDEA Research, International Digital Economy Academy, Shenzhen 518057, China
- Xuhui Jiang
- IDEA Research, International Digital Economy Academy, Shenzhen 518057, China
- Xinxin Fan
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Zhulin An
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Tingting Li
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Xuefei Li
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Zezhi Shao
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Tangwen Qian
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Tao Sun
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Boyu Diao
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Chuanguang Yang
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
- Chenqing Yu
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Yiqing Wu
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Mengxian Li
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Haifeng Zhang
- Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Yongcheng Zeng
- Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Zhicheng Zhang
- The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
- Zhengqiu Zhu
- College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
- Yiqin Lv
- College of Science, National University of Defense Technology, Changsha 410073, China
- Aming Li
- Center for Systems and Control, College of Engineering, Peking University, Beijing 100871, China; Center for Multi-Agent Research, Institute for Artificial Intelligence, Peking University, Beijing 100871, China
- Xu Chen
- Gaoling School of Artificial Intelligence, Renmin University of China, Beijing 100872, China
- Bo An
- College of Computing and Data Science, Nanyang Technological University, Singapore 639798, Singapore
- Wei Xiao
- School of Automation, Beijing Institute of Technology, Beijing 100081, China
- Chenguang Bai
- School of Electrical Engineering, Chongqing University, Chongqing 400044, China
- Yuxing Mao
- School of Electrical Engineering, Chongqing University, Chongqing 400044, China
- Zhigang Yin
- School of Electrical Engineering, Chongqing University, Chongqing 400044, China
- Sheng Gui
- Department of Mathematics, The University of Hong Kong, Hong Kong SAR 999077, China; LSEC, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China
- Wentao Su
- School of Food Science and Technology, Dalian Polytechnic University, Dalian 116034, China
- Yinghao Zhu
- National Engineering Research Center for Software Engineering, Peking University, Beijing 100871, China
- Junyi Gao
- Centre for Medical Informatics, University of Edinburgh, Edinburgh EH16 4UX, UK; Health Data Research UK, London NW1 2BE, UK
- Xinyu He
- Department of Stomatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China
- Yizhou Li
- Department of Stomatology, Yuquan Hospital, School of Clinical Medicine, Tsinghua University, Beijing 100040, China
- Guangyin Jin
- National Innovative Institute of Defense Technology, Beijing 100091, China
- Xiang Ao
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China
- Xuehao Zhai
- Department of Civil and Environmental Engineering, Imperial College London, London SW7 2AZ, UK
- Haoran Tan
- College of Electrical and Information Engineering, Hunan University, Changsha 410082, China
- Lijun Yun
- HUA-Innovation High-Tech (Hangzhou) Co., Ltd., Hangzhou 311100, China
- Hongquan Shi
- Dalian Naval Academy, Dalian 116018, China
- Jun Li
- School of Computer Science, China University of Geosciences, Wuhan 430078, China
- Changjun Fan
- College of Systems Engineering, National University of Defense Technology, Changsha 410073, China; Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China
- Kuihua Huang
- Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China
- Ewen Harrison
- Centre for Medical Informatics, University of Edinburgh, Edinburgh EH16 4UX, UK
- Victor C.M. Leung
- Shenzhen MSU-BIT University, Shenzhen 518172, China; Shenzhen University, Shenzhen 518060, China; The University of British Columbia, Vancouver, BC V6T 1Z4, Canada
- Sihang Qiu
- College of Systems Engineering, National University of Defense Technology, Changsha 410073, China; Corresponding author
- Yanjie Dong
- Shenzhen MSU-BIT University, Shenzhen 518172, China; Corresponding author
- Xiaolong Zheng
- The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; Corresponding author
- Gang Wang
- School of Automation, Beijing Institute of Technology, Beijing 100081, China; Corresponding author
- Yu Zheng
- JD Technology & JD Intelligent Cities Research, Beijing 101111, China; Corresponding author
- Yuanzhuo Wang
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; State Key Laboratory of AI Safety, Beijing 100190, China; Corresponding author
- Jiafeng Guo
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; State Key Laboratory of AI Safety, Beijing 100190, China; Corresponding author
- Lizhe Wang
- School of Computer Science, China University of Geosciences, Wuhan 430078, China; Corresponding author
- Xueqi Cheng
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; State Key Laboratory of AI Safety, Beijing 100190, China; Corresponding author
- Yaonan Wang
- College of Electrical and Information Engineering, Hunan University, Changsha 410082, China; Corresponding author
- Shanlin Yang
- School of Management, Hefei University of Technology, Hefei 230009, China; Corresponding author
- Mengyin Fu
- Nanjing University of Science and Technology, Nanjing 210094, China; Corresponding author
- Aiguo Fei
- School of Computer Science, National Pilot Software Engineering School, Beijing University of Posts and Telecommunications, Beijing 100876, China; Corresponding author
- Journal volume & issue
-
Vol. 6,
no. 6
p. 100948
Abstract
Intelligent decision-making (IDM) is a cornerstone of artificial intelligence (AI) designed to automate or augment decision processes. Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps, such as AI agents and high-level reinforcement learning. Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision, language, and sensory data—into a cohesive decision-making process. Foundation models (FMs) have become pivotal in science and industry, transforming decision-making and research capabilities. Their large-scale, multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare, life sciences, and education. This survey examines IDM’s evolution, advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains, highlighting the challenges and opportunities in building efficient, adaptive, and ethical decision systems. Public summary: • Decision intelligence evolved from rule-based to AI-driven, enabling adaptive, context-aware choices. • Foundation models unify knowledge to enable scalable, adaptive decision-making in healthcare and other fields. • The decision-making foundation model’s progress hinges on security, privacy, and human-AI ethics.
