I am a first-year CS Ph.D. student at National University of Singapore (NUS), supervised by Prof. Min-Yen Kan and Prof. Soujanya Poria. Previously, I obtained my Masterโ€™s degree in Computer Science and Bachelorโ€™s degree in Inforamtion Engineering from Shanghai Jiao Tong University (SJTU), fortunately advised by Prof. Weinan Zhang. I also work closely with Dr. Wenyue Hua, Prof. Liangming Pan, and Prof. Muning Wen.

Recently, my research mainly focus on LLM reasoning and AI agents, especially:

  • LLM mid-training and post-training.
  • LLM memory management and augmentation.
  • LLM-based multi-agent systems.

Feel free to reach out to me if you are interested in academic discussion / collaboration.

๐Ÿ”ฅ News

  • 2026.01: ย ๐ŸŽ‰๐ŸŽ‰ One paper KAIROS is accepted by ICLR 2026.
  • 2026.01: ย ๐ŸŽ‰๐ŸŽ‰ I will attend AAAI 2026 at Singapore during Jan 22-27, 2026. Letโ€™s connect!
  • 2025.10: ย ๐ŸŽ‰๐ŸŽ‰ I will attend EMNLP 2025 at Suzhou during Nov 5-7, 2025. Letโ€™s connect!
  • 2025.07: ย ๐ŸŽ‰๐ŸŽ‰ AntiLeak-Bench is selected as SAC Highlight at ACL 2025!
  • 2025.06: ย ๐ŸŽ‰๐ŸŽ‰ I will present our work RuleArena and AntiLeak-Bench at ACL 2025 in Vienna, Austria.
  • 2025.05: ย ๐ŸŽ‰๐ŸŽ‰ Two papers RuleArena and AntiLeak-Bench are accepted by ACL 2025 (Main).
  • 2025.04: ย ๐ŸŽ‰๐ŸŽ‰ I will present our work RuleArena at ICLR 2025 Workshops (Reason&Plan, SCI-FM). Hope to see you there.
  • 2025.04: ย ๐ŸŽ‰๐ŸŽ‰ I will join National University of Singapore (NUS) for my Ph.D. journey, starting Aug. 2025.

๐Ÿ“ Selected Publications

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

Junwei Liao, Haoting Shi, Ruiwen Zhou, Jiaqian Wang, Shengtao Zhang, Wei Zhang, Weinan Zhang, Ying Wen, Zhiyu Li, Feiyu Xiong, Bo Tang, Muning Wen

arXiv preprint ย  [ Paper | Code ]


Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems

Ruiwen Zhou*, Maojia Song*, Xiaobao Wu, Sitao Cheng, Xunjian Yin, Yuxi Xie, Zoey Hao, Wenyue Hua, Liangming Pan, Soujanya Poria, Min-Yen Kan

arXiv preprint ย  [ Paper | Code ]


MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Shengtao Zhang*, Jiaqian Wang*, Ruiwen Zhou, Junwei Liao, Yuchen Feng, Weinan Zhang, Ying Wen, Zhiyu Li, Feiyu Xiong, Yutao Qi, Bo Tang, Muning Wen

arXiv preprint ย  [ Paper | Code ]


From Atomic to Composite: Reinforcement Learning Enables Generalization in Complementary Reasoning

Sitao Cheng, Xunjian Yin, Ruiwen Zhou, Yuxuan Li, Xinyi Wang, Liangming Pan, William Yang Wang, Victor Zhong

arXiv preprint ย  [ Paper | Code ]


Measuring and Mitigating Rapport Bias of Large Language Models under Multi-Agent Social Interactions

Maojia Song, Tej Deep Pala, Ruiwen Zhou, Weisheng Jin, Amir Zadeh, Chuan Li, Dorien Herremans, Soujanya Poria

ICLR 2026 ย  [ Paper | Code ]


RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios

Ruiwen Zhou, Wenyue Hua, Liangming Pan, Sitao Cheng, Xiaobao Wu, En Yu, William Yang Wang

ACL 2025 ย  [ Paper | Code ]


AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Shuai Zhao, Anh Tuan Luu, William Yang Wang

ACL 2025 (Oral) | ๐Ÿ† SAC Highlight ย  [ Paper | Code ]


TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision

Ruiwen Zhou, Yingxuan Yang, Muning Wen, Ying Wen, Wenhao Wang, Chunling Xi, Guoqiang Xu, Yong Yu, Weinan Zhang

SIGIR 2024 ย  [ Paper | Code ]


๐ŸŽ– Honors and Awards

  • 2025.08 ย ย  NUS Research Scholarship.
  • 2024.11 ย ย  Huatai Securities Scholarship (~Top 10% out of 179).
  • 2024.11 ย ย  First-Class Excellence Scholarship (Top 30% out of 179).
  • 2022.11 ย ย  First-Class Excellence Scholarship (Top 30% out of 179).
  • 2021.12 ย ย  B-Class Excellence Scholarship (Top 10% out of 144).
  • 2021.12 ย ย  Zhiyuan Honors Scholarship (Top 5% students in Zhiyuan Honors Program).
  • 2021.04 ย ย  Outstanding Winner of MCM/ICM 2021 (~Top 0.15% among the world).
  • 2020.12 ย ย  A-Class Excellence Scholarship (Top 1 out of 144).
  • 2020.12 ย ย  National Scholarship (Top 2 out of 144).
  • 2020.12 ย ย  Zhiyuan Honors Scholarship (Top 5% students in Zhiyuan Honors Program).
  • 2019.11 ย ย  B-Class Excellence Scholarship (Top 10% out of 144).
  • 2019.11 ย ย  Zhiyuan Honors Scholarship (Top 5% students in Zhiyuan Honors Program).

๐Ÿ“– Educations

  • 2025.08 - Present, Ph.D. in Computer Science, NUS.
  • 2022.09 - 2025.03, M.Eng. in Computer Science and Technology, SJTU.
  • 2018.09 - 2022.06, B.Eng. in Information Engineering, SJTU.

๐Ÿ’ป Internships

  • 2026.04 - Present, MiniMax (Top Talent Intern), Mentored by: Junheng Zhang
  • 2024.07 - 2024.12, UCSB NLP Group, Advised by: Prof. William Yang Wang.
  • 2022.02 - 2023.02, Amazon Web Service, Mentored by: Quan Gan.
  • 2021.08 - 2022.01, Microsoft Research Asia, Mentored by: Kan Ren.

๐Ÿ‘€ Miscellaneous

In my spare time, I love:

  • Stroll: I often go for a walk to beautiful sites nearby and recover my energy.
  • Music: I listen to pop. songs, musicals, symphonies, etc. I also play the piano and sing.
  • Sports: I watch NBA, F1, etc. games. I am a fan of James Harden and Lewis Hamilton.