Rui Wang (王瑞)
Computer Science & Artificial Intelligence
I am a third-year undergraduate student at The Hong Kong University of Science and Technology (HKUST), pursuing a Bachelor of Engineering in Computer Science with an Extended Major in Artificial Intelligence. I completed a semester exchange at The University of Texas at Austin (UT Austin) in May 2026. I am currently working at AQUMON (Shenzhen) as an AI Large Language Model Research Intern through the HKUST CSE Co-op Program. I am also an incoming PhD student of Professor Yangqiu Song at CSE, HKUST.
My research interests broadly lie in Large Language Models (LLMs) and their reasoning capabilities. Specifically, I focus on:
- Decisions under risk and uncertainty
- Confidence calibration
- Robustness and adaptability
Feel free to reach out.
I always feel lucky to meet great mentors along my journey, including and not limited to, Mr. Jiayu Liu, Ms. Qing Zong.
🔥 News
📚 Publications
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Jiayu Liu, Qihan Lin, Cheng Qian, , Emre Can Acikgoz, Xiaocheng Yang, Jiateng Liu, Zhenhailong Wang, Xiusi Chen, Heng Ji, Dilek Hakkani-Tur
TL;DR: PlanBench-XL is an interactive benchmark with 327 retail tasks and 1,665 tools, showing that even leading LLM agents struggle with long-horizon planning in large, imperfect tool ecosystems.
Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty
, Qihan Lin, Jiayu Liu, Qing Zong, Tianshi Zheng, Dadi Guo, Haochen Shi, Weiqi Wang, Yangqiu Song
TL;DR: A three-stage evaluation grounded in Prospect Theory shows that LLM decision-making is not reliably described by the framework and becomes especially unstable under epistemic uncertainty.
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems
Jiayu Liu, , Qing Zong, Yumeng Wang, Cheng Qian, Qingcheng Zeng, Tianshi Zheng, Haochen Shi, Dadi Guo, Baixuan Xu, Chunyang Li, Yangqiu Song
TL;DR: NOVA is a noise-aware verbal confidence calibration framework that substantially improves the reliability of RAG systems when retrieved evidence is contradictory or irrelevant.
📝 Under Review
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
, Zishen Lai, Jiayu Liu, Cheng Qian, Jeonghwan Kim, Heng Wang, Xuejun Zhang, Jiateng Liu, Bingxuan Li, Shujin Wu, Qing Zong, Tianshi Zheng, Chunyang Li, Qihan Lin, Chen Li, Dadi Guo, Xiusi Chen, Yangqiu Song
TL;DR: AdaExploreBench benchmarks proactive exploration and test-time adaptation of LLM agents in evolving environments with hidden, drifting rules, revealing that agents struggle to actively acquire the right evidence and recognize when prior knowledge becomes stale.
AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era
Yunxiang Mo, Tianshi Zheng, Yisen Gao, , Newt Nguyen Kim Hue Nam, Kelvin Kiu Wai Tam, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See
TL;DR: AgentIdeaBench evaluates scientific ideation through matched static-observation and active-exploration settings across 33 LLMs and 40 subfields, revealing how agentic exploration affects the quality and originality of generated hypotheses.
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Qing Zong, Jiayu Liu, Junhao Shen, Zecong Tang, Linsi Wu, Yuxuan Liu, , Zhaowei Wang, Weiqi Wang, Cheng Qian, Xiusi Chen, Yangqiu Song
TL;DR: This survey proposes a progressive three-stage taxonomy of co-evolution in agentic systems — agent–agent, agent–environment, and meta co-evolution — laying a unified foundation for open-ended systems that improve beyond fixed human-designed paths.
🏫 Education
The Hong Kong University of Science and Technology
Sep 2023 - May 2027Bachelor of Engineering in Computer Science - Extended Major in AI
The University of Texas at Austin
Jan 2026 - May 2026Semester Exchange, Electronic and Computer Engineering
University College London
Jul 2024Summer School
💼 Internships
AQUMON
Jun 2026 - PresentAI Large Language Model Research Intern, Shenzhen
🤝 Services
Teaching Assistant
HKUSTCOMP1021: Introduction to Computer Science
Peer Mentor
HKUSTCSE Peer Mentor Program
🔗 Connect
I am always open to discussing research opportunities and collaborations. Please feel free to reach out.