Computer Science, Ph.D. Student The University of Hong Kong Email: liangcaisu@connect.hku.hk [Google Scholar] [GitHub] [LinkedIn]

About Me

I am a Ph.D. student at The University of Hong Kong, majoring in Computer Science. I am also a founder member of Deep Research Team at Tongyi Lab. Previously, I received my Master's degree in Computer Technology from Tsinghua University in 2024 and obtained my B.Eng degree in Software Engineering from Xidian University in 2021. I was a research intern supervised by Jieming Zhu and at Tencent mentored by Junwei Pan and Ximei Wang.

My research directions are Data Mining and Deep Research Agent.

News

• [Sep. 2025] We release our open-source and powerful deep research agent Tongyi DeepResearch! Please see the tech blog for details. Our model is available at huggingface and modelscope.
• [Sep. 2025] We release our work Scaling Agents via Continual Pre-training!
• [Aug. 2025] Our work ImportSnare was accepted by ACM CCS 2025. 🎉
• [Jan. 2025] One paper about unlearnable data was accepted by ICLR 2025. 🤩 See you in Singapore!
• [July. 2024] Our paper ERASE was accepted by CIKM 2024. Congrats to Ling-Hao Chen!

Research Experiences

• Tongyi Lab (Deep Research Team), Research Intern (Founder Member). May. 2025 -
• The University of Hong Kong, Research Assistant. Nov. 2023 - Aug. 2024
• Tencent, Research Intern. Jun. 2022 - Nov. 2023

Publications

(* denotes equal contributions)

• Tongyi-DeepResearch
  DeepResearch Team, Tongyi Lab
  Arxiv 2025. [📰 Blog] [🤗 HuggingFace] [ ModelScope] [ GitHub]

• Scaling Agents via Continual Pre-training
  Liangcai Su*, Zhen Zhang*, Guangyu Li*, Zhuo Chen*, Chenxi Wang*, Maojia Song, Xinyu Wang, et al.
  Arxiv 2025. [📄 Paper] [📰 VentureBeat]

• Towards General Agentic Intelligence via Environment Scaling
  Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang,
  Liangcai Su, Zhen Zhang, et al.
  Arxiv 2025. [📄 Paper]

• R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning
  Jiayi Lin, Liangcai Su, Junzhe Li, Chenxiong Qian.
  Arxiv 2025. [📄 Paper] [ GitHub] [🤗 HuggingFace]

• ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation
  Kai Ye, Liangcai Su, Chenxiong Qian.
  ACM CCS 2025. [📄 Paper][🏠 Homepage]

• How Far Are We from True Unlearnability?
  Kai Ye*, Liangcai Su*, Chenxiong Qian.
  ICLR 2025. [📄 Paper]

• STEM: Unleashing the Power of Embeddings for Multi-task Recommendation
  Liangcai Su*, Junwei Pan*, Ximei Wang, Xi Xiao, Shijie Quan, Xihua Chen, Jie Jiang.
  AAAI 2024. [📄 Paper] [ GitHub]

• Multi-interest Learning for Multi-modal Paper Recommendation
  Xiaoteng Shen*, Liangcai Su*, Xi Xiao, Yi Li
  ICASSP 2024. [📄 Paper]

• Beyond Two-Tower Matching: Learning Sparse Retrievable Interaction Models for Recommendation
  Liangcai Su, Fan Yan, Jieming Zhu, Xi Xiao, Haoyi Duan, Zhou Zhao, Zhenhua Dong and Ruiming Tang.
  SIGIR 2023. [📄 Paper]

[Show all publications]

Awards

• Outstanding Graduates of Beijing(北京市优秀毕业生), 2024.
• Best Report Award, The 15th Nanshan Academic Forum for Doctoral Students in the Guangdong-Hong Kong-Macao Greater Bay Area, 2023.
• ACM SIGIR 2023 Student Travel Award.
• Comprehensive Excellent Second-class Scholarship, Tsinghua University, 2022 & 2023 (Two times).
• National Scholarship(国家奖学金), 2019-2020. (Top 1% Student in XDU)
• National Scholarship(国家奖学金), 2017-2018. (Top 1% Student in XDU)