Wenjie Wang

About

I am an undergraduate researcher at Sichuan University. I am fortunate to conduct research under the supervision of Prof. Xiangliang Zhang and to work closely with Yue Huang. Their guidance has greatly influenced my research path toward intelligent, reliable, and data-efficient AI systems. My current interests include:

• RL & Agentic AI — enabling autonomous agents to learn, reason, plan, use tools, and collaborate.
• Trustworthy LLMs — improving the safety, robustness, alignment, and reliability of foundation models.
• Data-Centric AI — creating high-quality synthetic data, benchmarks, and evaluation pipelines for scalable model improvement.

Publications

^* Equal contribution / co-first authorship

1. SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data

   Wenjie Wang, Yue Huang, Zhengqing Yuan, Han Bao, Shiyi Du, Yuchen Ma, Yue Zhao, Yanfang Ye, Xiangliang Zhang

   EMNLP 2026 (Main Conference) · Paper · Code

2. Synthetic Interaction Data for Scalable Personalization in Large Language Models

   Yuchen Ma, Yue Huang, Wenjie Wang, Xiaonan Luo, Xiangliang Zhang, Stefan Feuerriegel

   KDD 2026 (D&B Track) · Paper · Code · Docs · Model · Data

3. RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems

   Yu Jiang*, Wenjie Wang*, Yue Huang, Yanbo Wang, Zhenhong Zhou, Xiuying Chen, Yang Liu, Pin-Yu Chen, Wei Wang, Xiangliang Zhang

   ACL 2026 (System Demonstrations) · Paper · Code · Docs

4. UXBench: Measuring the Actionability of LLM-Generated UX Critiques

   Wenjie Wang, Yue Huang, Zipeng Ling, Han Bao, Hang Hua, Xiaonan Luo, Yu Jiang, Shiyi Du, Yuexing Hao, Xiaomin Li, Yuchen Ma, Dianzhuo Wang, Yanfang Ye, Xiangliang Zhang

   Preprint · Paper · Code · Homepage

5. Emergent Social Intelligence Risks in Generative Multi-Agent Systems

   Yue Huang*, Yu Jiang*, Wenjie Wang*, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V. Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang

   NMI under review; ICML 2026 Workshop · Paper · Homepage

6. MemoHarness: Agent Harnesses That Learn from Experience

   Yue Huang*, Wenjie Wang*, Han Bao*, Yuchen Ma, Xiaonan Luo, Yi Nian, Haomin Zhuang, Zheyuan Liu, Yue Zhao, Xiangliang Zhang

   NeurIPS 2026 under review · Paper · Code

7. NARRA-Gym for Evaluating Interactive Narrative Agents

   Yue Huang, Yuchen Ma, Jiayi Ye, Wenjie Wang, Zipeng Ling, Xingjian Hu, Yuexing Hao, Zichen Chen, Zhangchen Xu, Yunhong He, Zhengqing Yuan, Yujun Zhou, Kehan Guo, Chaoran Chen, Toby Jia-Jun Li, Stefan Feuerriegel, Xiangliang Zhang

   NeurIPS 2026 under review · Paper · Code · Homepage

Awards

• National Scholarship | Ministry of Education of China 2025 Top 0.2% of undergraduates nationwide.
• National Scholarship | Ministry of Education of China 2024 Top 0.2% of undergraduates nationwide.
• Finalist | Mathematical Contest in Modeling (MCM), COMAP 2025 Top 2% of 27,000+ teams worldwide.
• Excellent Completion (National-level) | National Undergraduate Innovation Training Program 2025 Top 1% of 200+ projects.
• Second Prize | 21st Citi Financial Innovation Application Competition (Citi Cup) 2026 National finals.

Education

Sichuan University B.S. in Software Engineering, GPA: 3.89/4.0

Sep 2022 – Jun 2027 (expected)