My name is Moxin Li (李墨馨). I am a Postdoctoral Researcher at the College of Computing & Artificial Intelligence, University of Wisconsin–Madison, where I am fortunate to be advised by Prof. Sharon Li. Previously, I was a Postdoctoral Researcher at the National University of Singapore (NUS) in 2026, where I was fortunate to be advised by Prof. Mong Li Lee and Prof. Wynne Hsu. I received my Ph.D. from NUS, where I was fortunate to be advised by Prof. Tat-Seng Chua and mentored by Prof. Fuli Feng and Prof. Wenjie Wang. I received my bachelor's degree from Yuanpei College, Peking University, in 2020.

Research Interests

My research focuses on Trustworthy and Safe Agents. My current interests include:

• Long-Horizon Attacks: Evaluating agent vulnerabilities to multi-turn and cross-interaction attacks. [TROJail] [Plant, Persist, Trigger]
• Runtime Defense and Agent Harnesses: Developing runtime defenses and adaptive harnesses to improve agent safety while preserving task utility. [Harde] [Haste]
• Additionally, I am interested in agent skills and multi-agent collaboration.

I welcome opportunities for research collaboration. Feel free to reach out!

View My Resume

Publications and Preprints (Google Scholar, DBLP)

   *Equal Contribution
In the Year of 2026:

pdf	TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng ACL 2026

pdf	MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu ACL 2026

pdf	Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents Yongxiang Li, Moxin Li, Zhixin Ma, Fengbin Zhu, Dongrui Liu, Wenjie Wang, Fuli Feng arXiv preprint 2026

pdf	On Predicting the Post-training Potential of Pre-trained LLMs Xiaoyuan Li, Yubo Ma, Kexin Yang, Moxin Li, Keqin Bao, Wenjie Wang, Fuli Feng, Dayiheng Liu arXiv preprint 2026

pdf	ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning Xiaoyuan Li, Keqin Bao, Moxin Li, Yubo Ma, Yichang Zhang, Wenjie Wang, Fuli Feng, Dayiheng Liu arXiv preprint 2026

pdf	SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation Xiaoyuan Li, Yuzhe Wang, Moxin Li, Keqin Bao, Rui Men, Yichang Zhang, Dayiheng Liu, Wenjie Wang, Fuli Feng NeuRIPS 2025 (poster)

pdf	SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs Xiaoyuan Li, Moxin Li, Keqin Bao, Yubo Ma, Wenjie Wang, Dayiheng Liu, Fuli Feng arXiv preprint 2026

In the Year of 2025:

pdf	Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge Zhuo Liu, Moxin Li, Xun Deng, Qifan Wang, Fuli Feng EMNLP Findings 2025

pdf	Self-improvement towards pareto optimality: Mitigating preference conflicts in multi-objective alignment Moxin Li*, Yuantao Zhang*, Wenjie Wang, Wentao Shi, Zhuo Liu, Fuli Feng, Tat-Seng Chua ACL Findings 2025 Github

pdf	HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning Xiaoyuan Li, Moxin Li, Rui Men, Yichang Zhang, Keqin Bao, Wenjie Wang, Fuli Feng, Dayiheng Liu, Junyang Lin ACL Findings 2025

pdf	Knowledge Boundary of Large Language Models: A Survey Moxin Li*, Yong Zhao*, Yang Deng, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, Tat-Seng Chua ACL 2025 (Oral) Github

pdf	Counterfactual debating with preset stances for hallucination elimination of LLMs Yi Fang, Moxin Li, Wenjie Wang, Hui Lin, Fuli Feng COLING 2025

In the Year of 2024:

pdf	TAT-LLM: A Specialized Language Model for Discrete Reasoning over Financial Tabular and Textual Data Fengbin Zhu, Ziyang Liu, Fuli Feng, Chao Wang, Moxin Li, Tat Seng Chua ICAIF 2024

pdf	Think twice before trusting: Self-detection for large language models through comprehensive answer reflection Moxin Li, Wenjie Wang, Fuli Feng, Fengbin Zhu, Qifan Wang, Tat-Seng Chua EMNLP Findings 2024

pdf	Dual-Phase Accelerated Prompt Optimization Muchen Yang, Moxin Li, Yongle Li, Zijun Chen, Chongming Gao, Junqi Zhang, Yangyang Li, Fuli Feng EMNLP Findings 2024

pdf	Evaluating mathematical reasoning of large language models: A focus on error identification and correction Xiaoyuan Li, Wenjie Wang, Moxin Li, Junrong Guo, Yang Zhang, Fuli Feng ACL Findings 2024

pdf	Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua EMNLP 2024

In the Year of 2023:

pdf	Robust prompt optimization for large language models against distribution shifts Moxin Li, Wenjie Wang, Fuli Feng, Yixin Cao, Jizhi Zhang, Tat-Seng Chua EMNLP 2023 (Oral) Github

pdf	Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context Moxin Li, Wenjie Wang, Fuli Feng, Hanwang Zhang, Qifan Wang, Tat-Seng Chua ACL Findings 2023 Github

pdf	Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents with Semantic-Oriented Hierarchical Graphs Fengbin Zhu, Chao Wang, Fuli Feng, Zifeng Ren, Moxin Li, Tat-Seng Chua LREC-COLING 2024

pdf	Soargraph: Numerical reasoning over financial table-text data via semantic-oriented hierarchical graphs Fengbin Zhu, Moxin Li, Junbin Xiao, Fuli Feng, Chao Wang, Tat Seng Chua WWW 2023 (Workshop)

In the Year of 2022 and before:

pdf	Learning to imagine: Integrating counterfactual thinking in neural discrete reasoning Moxin Li, Fuli Feng, Hanwang Zhang, Xiangnan He, Fengbin Zhu, Tat-Seng Chua ACL 2022 Github

pdf	Hybrid learning to rank for financial event ranking Fuli Feng, Moxin Li, Cheng Luo, Ritchie Ng, Tat-Seng Chua SIGIR 2021 Github

pdf	Learning sense representation from word representation for unsupervised word sense disambiguation Jie Wang, Zhenxin Fu, Moxin Li, Haisong Zhang, Dongyan Zhao, Rui Yan AAAI 2020 (Student Abstract)

Professional Service and Presentation

Workshop Organizer: Personal Intelligence in the Agentic AI Era (PILA), KDD 2026 Registration Chair: ACM International Conference on AI in Finance (ICAIF), 2025 Tutorial Organizer: "Unveiling Knowledge Boundary of Large Language Models for Trustworthy Information Access" SIGIR 2025 Conference and Journal Reviewer: ACL, EMNLP, ICLR, NeurIPS, AAAI, KDD ... Conference Volunteer: ICAIF 2025, EMNLP 2024, WWW 2024, WSDM 2023 Session Chair and Presenter: The 2022, 2023, 2024 Singapore Symposium on Natural Language Processing Presenter: Singapore ACM SIGKDD Symposium 2024 Test Designer and Organizer: CCIR Cup 2022

Research Experience

Postdoctoral Researcher Aug. 2026 - Present College of Computing & Artificial Intelligence, University of Wisconsin–Madison Advisor: Prof. Sharon Li

Postdoctoral Researcher Jan. 2026 - July. 2026 Centre for Trusted Internet and Community, National University of Singapore Advisors: Prof. Mong Li Lee and Prof. Wynne Hsu

Research Intern Jul. 2025 - Jan. 2026 Sea AI Lab Advisors: Dr. Tianyu Pang

Research Intern Sep. 2020 - Jul. 2021 NExT Research Center, National University of Singapore Advisors: Prof. Tat-Seng Chua and Prof. Fuli Feng

Research Intern Jun. 2019 - Jun. 2020 Wangxuan Institute of Computer Technology, Peking University Advisor: Prof. Rui Yan

Education

School of Computing, National University of Singapore (NUS) Aug. 2021 - Mar. 2026, Singapore Ph.D. in Computer Science Advisor: Prof. Tat-Seng Chua Mentors: Prof. Fuli Feng and Prof. Wenjie Wang

Yuanpei College, Peking University (PKU) Sep. 2016 - Jun. 2020, Beijing Bachelor's Degree in Intelligent Science and Technology

Honors and Awards

Research Achievement Award,    2023    School of Computing, National University of Singapore