Publications

First & Co-First Author

• 

  SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents

  Xiaoyu Xu^†, Zi Liang^†, Minxin Du, Qipeng Xie, Qingqing Ye, Yuyuan Li, Haibo Hu

  arXiv 2026 · ^†Equal contribution (Paper) (Code) (Demo)

• 

  CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?

  Zi Liang^†, Xiaoyu Xu^†, Yanyun Wang, Minxin Du, Qingqing Ye, Haibo Hu

  arXiv 2026 · ^†Equal contribution (Paper) (Code) (Demo)

• 

  Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions

  Xiaoyu Xu, Minxin Du, Li Bai, Junxu Liu, Yaxin Xiao, Kun Fang, Liu Yang, Huadi Zheng, Peizhao Hu, Qingqing Ye, Haibo Hu

  Survey · arXiv 2026 (Paper)

• 

  When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents

  Xiaoyu Xu, Minxin Du, Qipeng Xie, Haobin Ke, Qingqing Ye, Haibo Hu

  arXiv 2026 (Paper) (Code) (Demo)

• 

  FIT to Forget: Robust Continual Unlearning for Large Language Models

  Xiaoyu Xu, Minxin Du, Kun Fang, Yaxin Xiao, Zhicong Huang, Cheng Hong, Qingqing Ye, Haibo Hu

  arXiv 2026 (Paper) (Code)

• 

  From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning

  Xiaoyu Xu, Minxin Du, Zitong Li, Zi Liang, Zhibiao Guo, Shiyu Zhang, Peizhao Hu, Qingqing Ye, Haibo Hu

  ACL 2026 Findings (Paper) (Code)

• 

  Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs

  Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye, Huadi Zheng, Peizhao Hu, Minxin Du, Haibo Hu

  ICML 2026 (Paper) (Code)

• 

  OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

  Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu

  EMNLP 2025 (Paper) (Code)

Coauthor

• 

  Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

  Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue

  ICML 2026 (Paper) (Code)