Innovative Research Award
Xu Cai
Ph.D. Candidate in Artificial Intelligence, China University of Mining and Technology, China
Xu Cai is a Ph.D. Candidate in Artificial Intelligence at the School of Information and Control Engineering, China University of Mining and Technology, China. His academic work focuses on distributed multi-agent path finding, graph neural networks, equivariant learning, evolutionary computation, and large-scale feature selection. His research contributions include optimization methodologies and intelligent coordination frameworks for complex artificial intelligence systems, supported by peer-reviewed publications and recognized scholarly impact.[1]
Abstract
This article summarizes the academic achievements, research profile, and scientific contributions of Xu Cai. His work spans artificial intelligence, distributed coordination systems, feature selection, evolutionary optimization, graph neural networks, and multi-agent learning. Through peer-reviewed publications and interdisciplinary collaborations, he has contributed to methodologies that address scalability, coordination efficiency, and optimization challenges in intelligent systems.[2]
Keywords
Distributed Multi-Agent Path Finding; Artificial Intelligence; Graph Neural Networks; Equivariant Learning; Evolutionary Computation; Multi-Objective Optimization; Large-Scale Feature Selection; Intelligent Coordination; Particle Swarm Optimization; Machine Learning.
Introduction
Xu Cai completed a master’s degree in Software Engineering at Nanjing University of Information Science and Technology in 2023 and subsequently pursued doctoral research in Artificial Intelligence. His academic activities have focused on advancing intelligent optimization algorithms and distributed decision-making mechanisms. These research directions address practical challenges in large-scale autonomous systems and data-intensive computational environments.[3]
Research Profile
The research portfolio of Xu Cai encompasses three major themes: distributed multi-agent path finding with conflict-aware coordination, equivariant learning frameworks, and evolutionary computation for large-scale feature selection. His collaborations involve researchers from China University of Mining and Technology, Nanjing University of Information Science and Technology, and international partners working in computational intelligence and optimization research.[4]
- Distributed Multi-Agent Path Finding (MAPF), Graph Neural Networks and Equivariant Learning, Evolutionary Computation, Multi-Objective Optimization, Large-Scale Feature Selection, Artificial Intelligence Coordination Systems
Research Contributions
One of the notable contributions of Xu Cai is the development of Conflict-Aware Dual-Level Coordination (CADC), a learning-based framework for distributed multi-agent path finding. The framework integrates Spatially-Aware Message Fusion (SAMF) and Adaptive Priority Coordination (APC) to improve communication and coordination among autonomous agents. Reported experimental evaluations demonstrated improved success rates and reduced flowtime metrics compared with baseline approaches in large-scale environments.[3]
His research in feature selection and evolutionary computation contributed to optimization strategies for high-dimensional classification tasks. Published studies explored self-adaptive particle swarm optimization and multi-objective evolutionary algorithms, improving solution quality and search efficiency across large-scale datasets.[4][5]
Publications
Xu Cai has authored and co-authored peer-reviewed journal publications in Engineering Applications of Artificial Intelligence, Applied Soft Computing, International Journal of Neural Systems, Journal of Ambient Intelligence and Humanized Computing, and ACM Transactions on Evolutionary Learning and Optimization. These publications collectively address distributed artificial intelligence, feature selection, optimization algorithms, and intelligent computational methodologies.[3][4][5][6]
- Engineering Applications of Artificial Intelligence, Applied Soft Computing, International Journal of Neural Systems, Journal of Ambient Intelligence and Humanized Computing, ACM Transactions on Evolutionary Learning and Optimization
Research Impact
According to the supplied academic metrics, Xu Cai has accumulated 181 Google Scholar citations across six indexed documents with an h-index of 4. Scopus records indicate documented citation activity and indexed publications. His work has received recognition through the Hojjat Adeli Award for Outstanding Contributions in Neural Systems, highlighting scholarly influence within optimization and intelligent systems research.[1][5]
Award Suitability
The academic profile of Xu Cai demonstrates sustained engagement in artificial intelligence research, interdisciplinary collaboration, peer-reviewed publication, and methodological innovation. His contributions to distributed coordination systems, feature selection, and optimization research provide documented evidence of scholarly productivity and technical advancement that align with the objectives commonly associated with research recognition programs and engineering innovation awards.[3][5]
Conclusion
Xu Cai is an emerging researcher in artificial intelligence whose work integrates distributed multi-agent systems, graph learning, evolutionary optimization, and feature selection methodologies. Through peer-reviewed publications, collaborative research activities, and recognized scientific contributions, his academic record reflects ongoing engagement with complex computational challenges and intelligent system development.[1][3]
External Links
References
- Google Scholar. (n.d.). Xu Cai Scholar Profile. https://scholar.google.com/citations?hl=zh-CN&user=truLrWwAAAAJ
- Elsevier. (n.d.). Scopus author details: Xu Cai, Author ID 57836867800. Scopus. https://www.scopus.com/authid/detail.uri?authorId=57836867800
- Cai, X., Zhai, Y., Neri, F., Liu, J., & Miao, Y. (2026). Conflict-aware dual-level coordination in distributed multi-agent path finding. Engineering Applications of Artificial Intelligence, 184, 116267. DOI: https://doi.org/10.1016/j.engappai.2026.116267
- Xue, Y., Cai, X., & Neri, F. (2022). A multi-objective evolutionary algorithm with interval based initialization and self-adaptive crossover operator for large-scale feature selection in classification. Applied Soft Computing, 127, 109420. DOI: https://doi.org/10.1016/j.asoc.2022.109420
- Zhang, C., Xue, Y., Neri, F., Cai, X., & Slowik, A. (2024). Multi-objective self-adaptive particle swarm optimization for large-scale feature selection in classification. International Journal of Neural Systems, 34(03), 2450014. DOI: https://doi.org/10.1142/S012906572450014X
- Xue, Y., Cai, X., & Jia, W. (2023). Particle swarm optimization based on filter-based population initialization method for feature selection in classification. Journal of Ambient Intelligence and Humanized Computing, 14(6), 7355–7366. https://link.springer.com/article/10.1007/s12652-022-04444-1