Yuxuan Liu

Yuxuan Liu

Ph.D. Student, HKUST

Hi, I am Yuxuan Liu (刘宇轩), a Ph.D. student at the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Yangqiu Song. Before joining HKUST, I received my Bachelor’s degree in Artificial Intelligence from Harbin Institute of Technology. I was also fortunate to intern at the Research Center for Social Computing and Information Retrieval (SCIR) under the guidance of Prof. Wanxiang Che.

📖 Education

  • Hong Kong University of Science and Technology (HKUST) Ph.D. student in the Department of Computer Science and Engineering, supervised by Prof. Yangqiu Song.

  • Harbin Institute of Technology Bachelor’s degree in the School of Future Technology (GPA: 92.89 / 100, Rank: 1 / 165).

🔬 Research Interests

I’m mainly interested in the research of Natural Language Processing.

  • Large Language Models
  • Recursive Self-Improvement
  • Harness Engineering

🔥 News

  • Aug 2026: Our paper SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision has been accepted to Findings of EMNLP 2026. [Paper] [Code]
  • Aug 2026: Our paper MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning has been accepted to Findings of EMNLP 2026. [Paper]
  • Aug 2026: Our paper Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design is available on arXiv. [Paper]
  • Aug 2026: Our paper Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs is available on arXiv. [Paper]
  • Aug 2026: Our paper Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds is available on arXiv. [Paper] [Code]
  • Jul 2026: Our paper RLPF: Reinforcement Learning from Performance Feedback for Code Generation is available on arXiv. [Paper]

📝 Publications

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Qing Zong, Jiayu Liu, Junhao Shen, Zecong Tang, Linsi Wu, Yuxuan Liu, Rui Wang, Zhaowei Wang, Weiqi Wang, Cheng Qian, Xiusi Chen, Yangqiu Song

arXiv preprint, 2026

[Paper] [Google Scholar]

Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs

Hongyu Luo, He Wang, Huihao Jing, Hong Ting Tsang, Yuxuan Liu, Wuganjing Song, Yauwai Yim, Chunyang Li, Yangqiu Song

arXiv preprint, 2026

[Paper] [Google Scholar]

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds

Yuxuan Liu, Zhaochen Su, Yuhao Zhang, Jiahe Guo, Zhongwei Xie, Huihao Jing, Lingyun Xie, Qing Zong, Yauwai Yim, Zhixiong Zhang, Haoran Li, Yangqiu Song

arXiv preprint, 2026

[Paper] [Code]

RLPF: Reinforcement Learning from Performance Feedback for Code Generation

Huihao Jing, Haozhe Cui, Wenbin Hu, Shaojin Chen, Haochen Shi, Changxuan Fan, Yuxuan Liu, Hanyu Yang, Sirui Zhang, Ziyi Chen, Haoran Li, Yangqiu Song

arXiv preprint, 2026

[Paper] [Google Scholar]

MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning

Kawai Chung, Chunkit Chan, Yauwai Yim, Yuxuan Liu, Haochen Shi, Weiqi Wang, Qing Zong, Tianshi Zheng, Yixuan Fu, Kai Chung Wong, Hao Liang, Yifan Gao, Xi Yang, Janet Hui-wen Hsiao, Yangqiu Song

Findings of EMNLP, 2026

[Paper] [Google Scholar]

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang, Qing Zong, Jiahe Guo, Zhongwei Xie, Yiyan Ji, Yauwai Yim, Hongyu Luo, Xiyu Ren, Chenyu Ruan, Haoran Li, Yangqiu Song

Findings of EMNLP, 2026

[Paper] [Code]

🏆 Honors & Awards

  • 2025.08 RedBird PhD Award Program
  • 2024.06 Top Ten Academic Tutoring Volunteers at Harbin Institute of Technology (Ranked 1st)
  • 2024.05 Meritorious Winner, Interdisciplinary Contest in Modeling
  • 2024.03 Song Qingling Future Scholarship
  • 2023.12 Shenzhen Stock Exchange Scholarship
  • 2023.11 First Prize, China Undergraduate Mathematical Contest in Modeling
  • 2023.10 Outstanding Student in Heilongjiang Province
  • 2023.10 Outstanding Student Model at Harbin Institute of Technology
  • 2022.10 National Scholarship (Ranked 1st)
  • 2022.07 First Prize, National University Students’ Opt-Sci-Tech Competition
  • 2022.05 Top Ten Learning Stars of the Fundamental Division at Harbin Institute of Technology
  • Multiple The Chinese Mathematics Competitions (Second in the same graduating class at HIT)
  • Multiple First-class People’s Scholarship in China * 6 (Top 3%)

💻 Experience

  • Center on Machine Learning Research Research intern, advised by Prof. Wangmeng Zuo.

  • Research Center for Social Computing and Information Retrieval (SCIR), Harbin Institute of Technology Research intern, advised by Prof. Wanxiang Che.