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.

My research interests broadly lie in Large Language Models (LLMs) and their reasoning capabilities. Specifically, I focus on:

  • LLM Decision-making
  • Uncertainty Quantification and Confidence Calibration
  • RAG Robustness
  • Rule Induction

Feel free to reach out - my contact information is available in the sidebar.

🔥 News

Jun 2026
💼 Currently interning at AQUMON (Shenzhen) as an AI Large Language Model Research Intern through the HKUST CSE Co-op Program, under the supervision of Prof. Yangqiu Song.
May 2026
📄 Submitted a new paper, "PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems", on evaluating long-horizon planning in large-scale tool ecosystems. [arXiv]
May 2026
📄 Updated the arXiv version of my paper "Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty", and resubmitted it to ARR May 2026 Cycle. [arXiv]
Apr 2026
🚀 Planning to start HKUST UG AI Lab with collaborator Jiayu Liu.
Jan 2026
📄 Submitted "NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems" to ACL 2026. [arXiv]
Jan 2026
✈️ Started semester exchange at The University of Texas at Austin.

📚 Research

PlanBench-XL Research Figure

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Under Review May 2026

Jiayu Liu, Qihan Lin, Cheng Qian, Rui Wang, Emre Can Acikgoz, Xiaocheng Yang, Jiateng Liu, Zhenhailong Wang, Xiusi Chen, Heng Ji, Dilek Hakkani-Tur

  • Introduced PlanBench-XL, an interactive benchmark with 327 retail tasks and 1,665 tools for evaluating long-horizon planning under retrieval-limited tool visibility
  • Showed that even leading models struggle to adapt when tool paths are blocked, highlighting major weaknesses in robust agentic planning for large, imperfect tool ecosystems
Rethinking Prospect Theory for LLMs Research Figure

Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

Under Review (COLM 2026) Apr 2026

Rui Wang, Qihan Lin, Jiayu Liu, Qing Zong, Tianshi Zheng, Dadi Guo, Haochen Shi, Weiqi Wang, Yangqiu Song

  • Designed a three-stage workflow to evaluate LLM decision-making under uncertainty, estimating Prospect Theory parameters and testing whether the framework meaningfully fits model behavior
  • Showed that Prospect Theory is not consistently reliable for interpreting LLMs, and that the inferred behavior is especially unstable under epistemic uncertainty expressed through linguistic markers
NOVA Research Figure

NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems

Under Review (ACL 2026) Jan 2026

Jiayu Liu, Rui Wang, Qing Zong, Yumeng Wang, Cheng Qian, Qingcheng Zeng, Tianshi Zheng, Haochen Shi, Dadi Guo, Baixuan Xu, Chunyang Li, Yangqiu Song

  • Proposed NOVA, a noise-aware verbal confidence calibration framework for RAG systems that improves reliability when retrieved evidence is contradictory or irrelevant
  • Built supervision from NOVA Rules and showed strong improvements in expected calibration error across both in-domain and out-of-domain settings

🏫 Education

The Hong Kong University of Science and Technology

Sep 2023 - May 2027

Bachelor of Engineering in Computer Science - Extended Major in AI

Cumulative GPA: 3.983 / 4.30
Major CGA: 4.073 / 4.30
Honors: Dean's List (All Semesters)
Scholarship: University Continuing Scholarship (Total 60,000 HKD)
Transcript: View PDF Here

The University of Texas at Austin

Jan 2026 - May 2026

Semester Exchange, Electronic and Computer Engineering

Coursework: Software Engineering, Machine Learning & Data Analytics for Edge AI

University College London

Jul 2024

Summer School

Programme: Short-term summer programme

💼 Internships

AQUMON

Jun 2026 - Present

AI Large Language Model Research Intern, Shenzhen

Program: HKUST CSE Co-op Program
Supervisor: Prof. Yangqiu Song
Focus: Large language models, reasoning, and applied AI research

🤝 Services

Teaching Assistant

HKUST

COMP1021: Introduction to Computer Science

Designed coding assignments and conducted tutorials for 50+ first-year undergraduates
Received positive feedback for clarifying complex CS concepts

Peer Mentor

HKUST

CSE Peer Mentor Program

Provided academic guidance and career planning advice to junior students
Fostered a collaborative learning environment

✉️ Get In Touch

Research Figure