Publications

See a full list of my papers on Google Scholar and DBLP.

Open-source Code

Preprints

1. Preprint Self-HPO: Self-Evolving Coding Agents via Harness–Policy Optimization [code]
   Zhepei Wei, Wenlin Yao, Baolin Peng, Danqing Wang, Qianhui Wu, Hao Cheng, Yu Meng, Jianfeng Gao

2. Preprint SecureVibe: Making Vibe Coding More Secure [code]
   Danqing Wang, Baolin Peng, Zhepei Wei, Isadora White, Wenlin Yao, Hao Cheng, Qianhui Wu, Minseon Kim, Xingdi Yuan, Lei Li, Jianfeng Gao

3. Preprint Negative Self-Distillation: Learning to Reason by Avoiding Flaws [code]
   Rongcan Pei, Zhepei Wei, Shuyao Xu, Xinyu Zhu, Wei-Lin Chen, Yu Meng

4. Preprint Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents [code]
   Yiding Wang, Zhepei Wei, Xinyu Zhu, Yu Meng

5. Preprint Do LLM Evaluators Prefer Themselves for a Reason? [code]
   Wei-Lin Chen, Zhepei Wei, Xinyu Zhu, Shi Feng, Yu Meng

2026

1. NeurIPS 2026 You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories [code]
   Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Chengsong Huang, Jiaxin Huang, Yu Meng

2. NeurIPS 2026 G-Zero: Self-Play for Open-Ended Generation from Zero Data [code]
   Chengsong Huang, Haolin Liu, Tong Zheng, Runpeng Dai, Langlin Huang, Jinyuan Li, Zongxia Li, Zhepei Wei, Yu Meng, Jiaxin Huang

3. ICML 2026 TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning [code]
   Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Sean Chen, Mohammad Kachuee, Teja Gollapudi, Tony Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong

4. ACL 2026 Aligning Large Language Models via Fully Self-Synthetic Data [code]
   Shangjian Yin, Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Yu Meng

5. ACL 2026 Findings PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
   Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

2025

1. NeurIPS 2025 The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning [code]
   Xinyu Zhu, Mengzhou Xia, Zhepei Wei, Wei-Lin Chen, Danqi Chen, Yu Meng

2. EMNLP 2025 WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning [code]
   Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li

3. EMNLP 2025 Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
   Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li

4. ICML 2025 AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism [code]
   Zhepei Wei, Wei-Lin Chen, Xinyu Zhu, Yu Meng. Previously presented at NeurIPS 2024 AFM Workshop (Oral: 8/157)

5. ICLR 2025 InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales [code] [webpage]
   Zhepei Wei, Wei-Lin Chen, Yu Meng

2024

1. ICLR 2024 Incentivized Truthful Communication for Federated Bandits
   Zhepei Wei, Chuanhao Li, Tianze Ren, Haifeng Xu, Hongning Wang

2023

1. NeurIPS 2023 Incentivized Communication for Federated Bandits
   Zhepei Wei, Chuanhao Li, Haifeng Xu, Hongning Wang

2022 and Before

1. EMNLP 2022 Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables
   Erxin Yu, Lan Du, Yuan Jin, Zhepei Wei, Yi Chang

2. AACL 2022 Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning
   Zhepei Wei, Yue Wang, Jinnan Li, Zhining Liu, Erxin Yu, Yuan Tian, Xin Wang, Yi Chang

3. IJCAI 2022 AttExplainer: Explain Transformer via Attention by Reinforcement Learning [code]
   Runliang Niu, Zhepei Wei, Yan Wang, Qi Wang

4. ACL 2020 A Novel Cascade Binary Tagging Framework for Relational Triple Extraction [code]
   Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang