I am a third-year graduate student at the School of Data Science and Engineering, East China Normal University, advised by Prof. Xiang Li in the PLANING (graPh mining and LANguage processING) lab.

My research explores how language models and agents can acquire external information, use it effectively, and learn from experience to solve future tasks. My work follows three connected directions:

• Acquiring external information. I develop methods to organize and retrieve external knowledge, making relevant information more accessible to models: MetaTox, E$^2$GraphRAG, CogGRAG, and CrossAug.
• Learning to use information in tasks. I study how training and agent design help models reason with evidence and use search to solve tasks: GRACE, Search Agent Review, and Think Big, Search Small.
• Distilling experience for future tasks. I study how models and agents turn experience into reusable knowledge and capabilities for future problem solving: Skill0.5, LazyMem, and S$^2$D-OPD.

★★★ Feel free to reach out to me for academic discussions and collaborations!

🔥 News

• 2026.10 🌱🌱 My work has surpassed 100 citations on Google Scholar. A milestone—keep moving!
• 2026.09 🎉🎉 A new paper, Not Every Token Is Worth Distilling, is out on arXiv. Enjoy!
• 2026.05 🎉🎉 4 new papers released on ArXiv, enjoy!
• 2026.04 🔥🔥 Our work RATE is accepted by ACL 2026, see you in CA!
• 2026.01 🎊🎊 Happy New Year! A recent work GRACE has been released on ArXiv!

  📑 Publications

• EMNLP 2026 MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment,
  Zixuan Yang, Yibo Zhao, Weicong Liu, Xiang Li.

• EMNLP 2026 Findings APEX: Academic Poster Editing Agentic Expert,
  Chengxin Shi*, Qinnan Cai*, Zeyuan Chen*, Long Zeng*, Yibo Zhao, Jing Yu, Jianxiang Yu, Xiang Li.

• EMNLP 2026 Findings Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning,
  Jiapeng Zhu, Jianxiang Yu, Yibo Zhao, Chengcheng Han, Qi Gu, Xunliang Cai, Xiang Li, Weining Qian.

• EMNLP 2026 Findings Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG,
  Jiaming Zhang, Yibo Zhao, Jing Yu, Jianxiang Yu, Xiang Li.

• ACL 2026 RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems,
  Weicong Liu*, Zixuan Yang*, Yibo Zhao, Xiang Li.

• AAAI 2026 Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving,
  Yao Cheng, Yibo Zhao, Jiapeng Zhu, Yao Liu, Xing Sun, Xiang Li.

• EMNLP 2025 Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization,
  Jing Yu*, Yibo Zhao*, Jiapeng Zhu, Wenming Shao, Bo Pang, Zhao Zhang, Xiang Li.

• ACL 2025 Findings Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph,
  Yibo Zhao, Jiapeng Zhu, Can Xu, Yao Liu, Xiang Li.

📜 Preprints

• Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD,
  Yibo Zhao*, Zixuan Yang*, Yunshi Lan, Xiang Li.

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

• E$^2$GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness,
  Yibo Zhao, Jiapeng Zhu, Jianxiang Yu, Ye Guo, Kangkang He, Xiang Li.

• GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence,
  Yibo Zhao, Jiapeng Zhu, Zichen Ding, Xiang Li.

• Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?,
  Qinnan Cai*, Yibo Zhao*, Xiang Li.

• LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory,
  Jing Yu, Yibo Zhao, Jiaming Zhang, Xiang Li.

• OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards,
  Zehao Li, Zhenyu Wu, Yibo Zhao, Bowen Yang, Jingjing Xie, Zhaoyang Liu, Zhoumianze Liu, Kaiming Jin, Jianze Liang, Zonglin Li, Feng Wu, Bowen Zhou, Zun Wang, Zichen Ding.

📖 Educations

• 2024.09 - now, Post-graduate student, Data Science and Engineering, East China Normal University
• 2020.09 - 2024.06, Undergraduate, School of Communication, East China Normal University.

💻 Internships

• 2025.12 - 2026.09 Post-training Intern, LLM Center, AI Lab , Shanghai, China. Mentor: Zichen Ding.

📚 Teaching

• 2025–2026 Fall, Teaching Assistant, Contemporary Artificial Intelligence (undergraduate level), East China Normal University (ECNU), China.

🔍 Service

• I serve(d) as a reviewer for the following venues:
  • KDD 2027 (Cycle 1), COLM 2026, ACL Rolling Review (ARR).

🎲 Fun Facts

Amor fati.