Jiayi Wu

Jiayi Wu

I am a 4th-year Ph.D. student at the School of Data Science and Engineering, East China Normal University (ECNU DASE), advised by Prof. Ming Gao and Prof. Xiang Li. I have interned at Baidu Search, Tencent Hunyuan, and ByteDance Volcengine Ark.

My research focuses on:

  • Retrieval-Augmented Generation (RAG)
  • Search Agents
  • LLM Post-training & Alignment (RL for LLM Agents)

I will graduate in June 2027 and am currently looking for full-time opportunities in LLM and Agent research/engineering. Feel free to reach out via wujwyi@126.com.

🔥 News

  • 2026.08:  Paper “Negative Advantage Is a Double-Edged Sword” accepted to EMNLP 2026 Findings.
  • 2026.08:  Paper “Node-to-Neighborhood Semantic Consistency” accepted to EMNLP 2026 Findings.
  • 2026.06:  Joined ByteDance Volcengine Ark as an LLM Algorithm Intern.
  • 2026.04:  🏆 Received the Tencent Best Patent Team Award (鹅厂好专利团队奖) as first inventor.
  • 2026.04:  Paper “Adversarial Yet Cooperative” accepted to ACL 2026 Findings.
  • 2026.04:  Paper “ImCoref-CeS” accepted to ACL 2026.
  • 2026.04:  Released our new preprint “Negative Advantage Is a Double-Edged Sword: Calibrating Advantages in GRPO for Search Agents” on arXiv.
  • 2025.06:  Joined Tencent Hunyuan team as a Research Intern via the Rhino-Bird Elite Talent Program (犀牛鸟精英人才计划).
  • 2025.06:  New preprint “Towards AI Search Paradigm” — Baidu Search technical report; core techniques of PA-RAG deployed in Baidu Search production.
  • 2025.04:  Attended NAACL 2025 in Albuquerque, USA, and presented PA-RAG.
  • 2025.01:  Our paper “PA-RAG” accepted to NAACL 2025 Main Conference.
  • 2024.09:  Our paper “Cross-model Control” accepted to NeurIPS 2024.
  • 2024.09:  Paper “AdaSwitch” accepted to EMNLP 2024 Main Conference.
  • 2024.02:  Our paper “Structure-aware Fine-tuning for Code Pre-trained Models” accepted to LREC-COLING 2024.

📝 Publications

  • Negative Advantage Is a Double-Edged Sword: Calibrating Advantages in GRPO for Search Agents
    Jiayi Wu, Ruobing Xie, Zeqian Huang, Lei Jiang, Can Xu, Kangyang Luo, Bochen Lin, Ming Gao, Xiang Li.
    EMNLP 2026 Findings. [Paper] [Code]

  • PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
    Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao.
    NAACL 2025 Main Conference. Core techniques deployed in Baidu Search production. [Paper] [Code]

  • Cross-model Control: Improving Multiple Large Language Models in One-time Training
    Jiayi Wu, Hao Sun, Hengyi Cai, Lixin Su, Shuaiqiang Wang, Dawei Yin, Xiang Li, Ming Gao.
    NeurIPS 2024. [Paper] [Code]

  • Structure-aware Fine-tuning for Code Pre-trained Models
    Jiayi Wu, Renyu Zhu, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao.
    LREC-COLING 2024. [Paper] [Code]

  • Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieval-Augmented Language Models
    Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li.
    ACL 2026 Findings. [Paper]

  • Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection
    Bochen Lin, Jianxiang Yu, Jiayi Wu, Lin Qi, Huang Lu, Xiang Li.
    EMNLP 2026 Findings. [Paper]

  • ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement
    Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun.
    ACL 2026. [Paper]

  • Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?
    Yibo Zhao, Zichen Ding, Jiayi Wu, Zun Wang, Xiang Li.
    arXiv preprint, 2026. [Paper]

  • Deep Research: A Systematic Survey
    Zhengliang Shi, Yiqun Chen, Haitao Li, Weiwei Sun, Shiyu Ni, Yougang Lyu, Run-Ze Fan, Bowen Jin, Yixuan Weng, Minjun Zhu, Qiujie Xie, Xinyu Guo, Qu Yang, Jiayi Wu, Jujia Zhao, Xiaqiang Tang, Xinbei Ma, Cunxiang Wang, Jiaxin Mao, Qingyao Ai, Jen-Tse Huang, Wenxuan Wang, Yue Zhang, Yiming Yang, Zhaopeng Tu, Zhaochun Ren.
    arXiv preprint, 2025. [Paper]

  • Towards AI Search Paradigm
    Yuchen Li, Hengyi Cai, Rui Kong, Xinran Chen, Jiamin Chen, Jun Yang, Haojie Zhang, Jiayi Li, Jiayi Wu, Yiqun Chen, Changle Qu, Wenwen Ye, Lixin Su, Xinyu Ma, Lingyong Yan, Long Xia, Daiting Shi, Junfeng Wang, Xiangyu Zhao, Jiashu Zhao, Haoyi Xiong, Shuaiqiang Wang, Dawei Yin.
    Baidu Search Technical Report, 2025. [Paper]

  • Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation
    Shuo Zhang, Xiao Li, Jiayi Wu, Fan Yang, Xiang Li, Ming Gao.
    arXiv preprint, 2025. [Paper]

  • AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning
    Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin.
    EMNLP 2024 Main Conference. [Paper]

💻 Internships

  • ByteDance, Volcengine Ark  ·  2026.06 – Present
    LLM Algorithm Intern.

  • Tencent, Hunyuan  ·  2025.06 – 2026.06
    Research Intern, mentored by Ruobing Xie.

  • Baidu, Search Strategy Department  ·  2023.08 – 2025.06
    Research Intern in Dawei Yin’s group, mentored by Hengyi Cai and Lingyong Yan.

📖 Education

  • East China Normal University (ECNU)  ·  2022.09 – 2027.06 (expected)
    Ph.D. in Software Engineering, School of Data Science and Engineering.

  • Zhejiang University of Technology (ZJUT)  ·  2018.09 – 2022.06
    B.S. in Computer Science and Technology.

🎖 Honors and Awards

  • 2026  Tencent Best Patent Team Award (鹅厂好专利团队奖) (as first inventor).
  • 2021  Finalist (Top 1.8%), MCM/ICM Mathematical Contest in Modeling.
  • 2020  National First Prize, China Undergraduate Mathematical Contest in Modeling (全国大学生数学建模竞赛).

🔍 Academic Services

  • Reviewer: NeurIPS 2025 · ACL Rolling Review (5 cycles, 2025–2026)