# About

I'm a Ph.D. student at Purdue University, advised by Prof. Jing Gao and Prof. Xiaoqian Wang. My research focuses on LLM agents, reinforcement learning and post-training, and AI safety, with the goal of making language models more capable, efficient, and trustworthy.

I develop methods for language models to learn from shared experience, for agents to communicate and act proactively, and for model developers to identify and mitigate safety risks. My recent work includes reinforcement learning across heterogeneous models, latent-space agent communication, efficient proactive agents, and copyright compliance through unlearning and agent-based defenses.

I have interned at Microsoft Research and Amazon Web Services, working on proactive agents and reinforcement learning for language models, respectively. My work has been accepted to NeurIPS, ICLR, COLM, and EMNLP.

I'm open to research collaborations and new graduate opportunities in industry, particularly Research Scientist and Applied Scientist roles. Feel free to reach out via LinkedIn!

# News

• [Sep 2026] Our paper on tokenizer transplantation across large language models has been accepted to NeurIPS 2026.
• [Sep 2026] Our paper on cross-scenario generality of agentic memory systems has been accepted to AACL-IJCNLP 2026.
• [Jun 2026] I started my summer Research Internship at Microsoft Research in Redmond.
• [May 2026] We introduce a graph-first architecture for proactive-agent triggering and routing, asking whether always-on agents really need an LLM to decide when to wake and what to anchor.
• [May 2026] Selected as a Gold Reviewer for ICML 2026. Wrote up some reflections on both sides of LLM-assisted peer review this cycle.
• [May 2026] We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience while keeping separate parameters, objectives, and tokenizers.
• [Mar 2026] I will be joining Microsoft Research - Deep Learning Group this upcoming summer as a Research Intern.
• [Feb 2026] We introduce Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems, a text-free communication framework that uses a Universal Visual Codec to enable efficient latent-space transfer across heterogeneous VLM agents. Code is available here.
• [Jan 2026] We release tokenforge, a study of tokenizer transplantation in modular model merging. We show how the standard merging pipeline can map seemingly inert donor-model tokens into high-salience downstream features.
• [Jul 2025] SUV, a scalable copyright compliance framework for large language models (LLMs) with regularized selective unlearning, is accepted by COLM 2025.
• [May 2025] I joined AWS AI Fundamental Research Team as an Applied Scientist Intern for Summer 2025.
• [May 2025] I will present a portion of the tutorial, LLMs and Copyright Risks: Benchmarks and Mitigation Approaches, at NAACL 2025.
• [Jan 2025] FedBiscuit accepted by ICLR 2025.
• [Jan 2025] CausalEval accepted by NAACL 2025.
• [Jan 2025] Survey on Factuality in Large Language Models accepted by ACM Computing Surveys.
• [Dec 2024] GraphEval accepted by IEEE Data Engineering Bulletin.
• [Nov 2024] Listed as one of the Top Reviewers for NeurIPS 2024.
• [Sep 2024] Two papers accepted to EMNLP 2024 Main Conference: SHIELD and SaySelf.

# Recent Publications

Selected first-author and co-first-author work. # denotes equal contribution. See the full publication list for the complete local list, or Google Scholar for live citation counts.

1. Do Proactive Agents Need an LLM to Decide When to Act? Xiaoze Liu, Ruowang Zhang, Amir H. Abdi, Michel Galley, Zhikai Chen, Siheng Xiong, Xiaoqian Wang, Jing Gao, Preprint, 2026. Blog

2. Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models. Xiaoze Liu, Dhananjay Ram, Yuting Zhang, Zhaoyang Zhang, Wei Xia, Stefano Soatto, Preprint, 2026. Blog

3. Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems. Xiaoze Liu#, Ruowang Zhang#, Weichen Yu, Siheng Xiong, Liu He, Feijie Wu, Hoin Jung, Matt Fredrikson, Xiaoqian Wang, Jing Gao, Preprint, 2026. Blog · Code

4. When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models. Xiaoze Liu, Weichen Yu, Matt Fredrikson, Xiaoqian Wang, Jing Gao, The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026. Blog

5. SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning. Tianyang Xu#, Xiaoze Liu#, Feijie Wu, Xiaoqian Wang, Jing Gao, The 2025 Conference on Language Modeling (COLM), 2025. Blog

6. SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation. Xiaoze Liu#, Ting Sun#, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, Jing Gao, The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. Blog

# Invited Talks & Tutorials

1. LLMs and Copyright Risks: Benchmarks and Mitigation Approaches. NAACL 2025 Tutorials, May 2025. Delivered part of the tutorial session live on Zoom. Tutorial organized by Prof. Zhaozhuo Xu and Prof. Denghui Zhang.

2. SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation. NICE NLP, November 2024. Delivered talk in Mandarin on mitigating copyright violation via SHIELD.

# Education and Experience

• PhD Student, Purdue University, 2023 - Present
  • Advised by Prof. Jing Gao and Prof. Xiaoqian Wang
  • Research Intern, Microsoft Research - Deep Learning Group, Summer 2026, with Michel Galley, Amir H. Abdi, and Marjan Albooyeh.
  • Applied Scientist Intern, AWS AI Fundamental Research Team, Summer 2025, with Dhananjay Ram and Yuting Zhang.
• Master's Degree, Zhejiang University, 2020 - 2023
  • Awarded Outstanding Master's Thesis of Zhejiang Province (122 out of 35,149, Top 0.3%), and Excellent Postgraduate student's Award of Zhejiang University.
  • Research Intern, Alibaba DAMO Academy (now Tongyi Lab), Sep 2022 - 2023, with Yong Jiang.
  • Research Intern, Alibaba Cloud, 2021 - Jul 2022
• Bachelor's Degree, Northeastern University, 2016 - 2020
  • Awarded the National Scholarship of China (Top 0.2%) twice during undergraduate studies, and the Outstanding Graduate of Northeastern University in 2020.
  • Software Engineering Intern, ByteDance, TikTok server backend, 2019 - 2020
  • Exchange Student, Kanazawa University, 2019, Supported by JASSO Scholarship

# Academic Services

Serve as a reviewer/PC for

• 2026: ICML (Gold Reviewer), NeurIPS, ACL Rolling Review, KDD
• 2025: ICLR, ICML, NeurIPS, ACL Rolling Review, KDD
• 2024: NeurIPS (Top Reviewer), ACM MM, SDM, CIKM, ISWC, ACL Rolling Review, KDD
• 2023: NeurIPS, EMNLP, KDD

Served as a Journal reviewer for Transactions on Machine Learning Research, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Neural Networks and Learning Systems, Pattern Recognition, Information Sciences, IEEE Transactions on Big Data