I am Minzheng Wang, a third-year Ph.D student at MAIS, Institute of Automation, Chinese Academy of Sciences, supervised by Nan Xu and Wenji Mao. Before that, I received my bachelor’s degree from Beijing Institute of Technology in 2023. I am now a research intern at the miHoYo AI Team. Before that, I have also spent time at the Tongyi Lab, Alibaba Group as a Research Intern, mentored by Xinghua Zhang.
Research 🔍
I am broadly interested in natural language processing and large language models. My current research focuses on 1) LLM-based Language Agent, 2) Socially Intelligent Agent, and 3) LLM-based RL. I’m open to discussing potential partnerships and collaboration. Please feel free to reach out if you’re interested in working together.
News 📰
[2026.01] Got one papers accepted by ICLR 2026, congrats to all co-authors🎉!
[2025.09] Got one papers accepted by EMNLP 2025, congrats to all co-authors🎉!
[2025.05] Got two papers accepted by ACL 2025, congrats to all co-authors🎉!
[2025.04] My paper has been cited 100 times on Google Scholar, a small milestone for me!
[2025.01] Got one papers accepted by NAACL 2025, congrats to all co-authors🎉!
[2025.01] Got one papers accepted by AAAI 2025, congrats to all co-authors🎉!
[2024.09] (Oral) Got one paper accepted by EMNLP 2024, congrats to all co-authors🎉!
[2024.07] Got one papers accepted by COLM 2024, congrats to all co-authors🎉!
[2024.04] Joined the Tongyi Lab, Alibaba Group as a Research Intern, mentored by Xinghua Zhang.
[2024.02] (Oral) Got one paper accepted by COLING 2024, congrats to all co-authors🎉!
[2023.09] Joined the MAIS, Institute of Automation, Chinese Academy of Sciences as a Ph.D student, supervised by Wenji Mao.
[2023.06] Graduated from Beijing Institute of Technology with a bachelor’s degree in Automation 🎓.
[2022.09] Joined the Wenge Group as a Research Intern, mentored by Nan Xu.
Publications 📑
Most recent publications on Google Scholar.
First Author 1️⃣
(* indicates equal contribution)
Adaptive Social Learning via Mode Policy Optimization for Language Agents
Minzheng Wang, Yongbin Li, Haobo Wang, Xinghua Zhang, Nan Xu, Bingli Wu, Fei Huang, Haiyang Yu, Wenji Mao
Proceedings of ICLR 2026. (Scores: 8 8 8 6) [link] [code]
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Yuqiao Tan*, Minzheng Wang*, Shizhu He, Huanxuan Liao, Chengfeng Zhao, Qiunan Lu, Tian Liang, Jun Zhao, Kang Liu
Under Review. [link] [code]
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
Minzheng Wang, Run Luo, Yanbo Wang, Zichen Liu, Yuqiao Tan, Tao Tan, Longze Chen, Jiaming Li, Nan Xu, Lu Wang, Wenji Mao
Under Review.
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li
Findings of ACL 2025. [link] [code]
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Minzheng Wang*, Longze Chen*, Cheng Fu, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li
Proceedings of EMNLP 2024 (Oral). [link] [code]
PromISe: Releasing the Capabilities of LLMs with Prompt Introspective Search
Minzheng Wang, Nan Xu, Jiahao Zhao, Yin Luo, Wenji Mao
Proceedings of COLING 2024 (Oral). [link] [code]
Co-authored Papers 🤝
ImaRA: An Imaginative Frame Augmented Method for Low-Resource Multimodal Metaphor Detection and Explanation
Yuan Tian, Minzheng Wang, Nan Xu, Wenji Mao
Findings of NAACL 2025. [link]
Enhancing Adversarial Robustness of LLMs with Analytic Hierarchy Process
Jiahao Zhao, Minzheng Wang, Nan Xu, Wenji Mao
Proceedings of COLM 2024. [link]
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
Tao Zou, Xinghua Zhang, Haiyang Yu, Minzheng Wang, Fei Huang, Yongbin Li
Proceedings of EMNLP 2025. [link]
Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs
Lei Zhang, Yunshui Li, Jiaming Li, Xiaobo Xia, Jiaxi Yang, Run Luo, Minzheng Wang, Longze Chen, Junhao Liu, Min Yang
Proceedings of AAAI 2025. [link] [code]
The imperative of conversation analysis in the era of llms: A survey of tasks, techniques, and trends
Xinghua Zhang, Haiyang Yu, Yongbin Li, Minzheng Wang, Longze Chen, Fei Huang
Arxiv 2024. [link]
Mmevol: Empowering multimodal large language models with evol-instruct
Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Xiaobo Xia, Fei Huang, Jingkuan Song, Yongbin Li
Findings of ACL 2025. [link] [code]
Yayi-uie: A chat-enhanced instruction tuning framework for universal information extraction
Xinglin Xiao, Yijie Wang, Nan Xu, Yuqi Wang, Hanxuan Yang, Minzheng Wang, Yin Luo, Lei Wang, Wenji Mao, Daniel Zeng
Arxiv 2023. [link] [code] [model]
Yayi 2: Multilingual open-source large language models
Wenge Group
Arxiv 2023. [link] [code] [model]
Services 💬
Reviewer for ICLR (2026), ACL (2026, 2025), EMNLP (2025), AAAI (2025), NLPCC (2025), IEEE Intelligent Systems (2024)
Awards 🥇
Merit Student, University Chinese Academy of Sciences (2024)
Outstanding Graduate of Beijing (2023)
Outstanding Graduate of Beijing Institute of Technology (2023)
Merit Student, Beijing Institute of Technology (2019-2023)