Zixuan Wang
MPhil in Artificial Intelligence
PhD Applicant
HKUST(GZ) AI Thrust
Guangzhou, China
Hong Kong University of Science and Technology (Guangzhou)
zwang933@connect.hkust-gz.edu.cn
Send EmailResearch Interests
About
Hi, I'm Zixuan Wang, an MPhil student in Artificial Intelligence at the Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Chengwei Qin. I received my BSc(Hons) in Data Science from Hong Kong Baptist University.
During my undergraduate studies, Prof. Donglong Chen supervised my thesis on AI security, which became the UNGIA paper at IJCNN 2026. Assoc. Prof. Raymond Shu Tak Lee mentored my competition and project work and introduced me to NLP and agents.
My research focuses on AI long-term memory and lifelong learning, multi-agent orchestration, and personalized agents. I study how agents can retain and update useful knowledge over long interactions, retrieve it when a future situation calls for it, and coordinate specialized capabilities to serve individual users.
Seeking PhD opportunities. I am looking for a PhD position aligned with my research interests in AI long-term memory, multi-agent systems, and personalized agents. Please feel free to contact me if our interests align.
Selected Publications
View All →* Equal contribution (co-first authors)
Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems
Zhe Yu*, Zixuan Wang*, Peidong Wang, Hehai Lin, Ruochen Zhao, Chengwei Qin
arXiv preprint arXiv:2610.08101 · Submitted to ICLR 2027
Defines execution consistency beyond accurate shared memory and studies evidence-based diagnosis and recovery in multi-agent workflows.
MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification
Hehai Lin*, Zixuan Wang*, Ming Yan*, Peidong Wang, Shilei Cao, Minzhi Li, Bosheng Ding, Juepeng Zheng, Chengwei Qin
arXiv preprint arXiv:2610.17613 · Submitted to ICLR 2027
Uses node-level utility and interaction strength to guide multi-agent design, runtime editing, and post-hoc error attribution.
AMA: Adaptive Memory via Multi-Agent Collaboration
Weiquan Huang*, Zixuan Wang*, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin
Findings of the Association for Computational Linguistics: ACL 2026
Coordinates agents to construct, retrieve, verify, and refresh long-term memory across multiple granularities.
BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications
Jianing Hao, Yuhe Wu, Yuanjian Xu, Shichang Meng, Shuai Yuan, Wei Zeng, Zixuan Wang, Guang Zhang
Findings of the Association for Computational Linguistics: ACL 2026
Benchmarks how foundational business knowledge supports LLM reasoning in practical applications.
T-Mem: Memory That Anticipates, Not Archives
Weidong Guo, Dakai Wang, Zixuan Wang, Hui Liu, Yu Xu
EMNLP 2026 Main Conference (accepted)
Long-term conversational memory that prepares associative as well as descriptive retrieval cues at write time.
Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems
Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin
EMNLP 2026 Main Conference (accepted)
Generates and optimizes domain-specific nodes to improve automatic multi-agent system construction.
News
Beyond Corrected Memory, MAS-Gate, and Degrees of Freedom in Multi-Agent Coordination are now available as arXiv preprints and have been submitted to ICLR 2027.
T-Mem and Unified-MAS were accepted to the EMNLP 2026 Main Conference.
AMA and BizCompass appeared in Findings of ACL 2026.
Started my MPhil in Artificial Intelligence at HKUST(GZ), working with Prof. Chengwei Qin.
Graduated from Hong Kong Baptist University with a BSc(Hons) in Data Science.
Completed research assistant work at the Guangdong Province Key Laboratory of Interdisciplinary Research and Application for Data Science.
Received a Bronze Medal in the Kaggle LLM Prompt Recovery Competition.
Started a data analyst internship at Vivo Mobile Communication Co., Ltd., focusing on product analysis, dashboards, and data-assistant LLM work.