I am now a senior researcher at Tencent Youtu Lab, specializing in the research of Large Language Model-based techniques, e.g., GraphRAG and Agents. I obtained my Ph.D. degree from The Hong Kong Polytechnic University, Department of Computing, supervised by Prof. Xiao Huang and Prof. Qing Li. I was nominated by both the Department of Computing and the Faculty of Computer and Mathematical Science of Hong Kong Polytechnic University as the ‘Best Research Postgraduate Student’ of 2024.
My current research interests focus on Large Language Models, Agents and Knowledge Graphs, especially in exploring GraphRAG and Graph-enhanced Agents for various domains-specific scenarios.
We are actively recruiting ‘Qingyun’ Talent Program graduates and research interns for exploration on GraphRAG and Agents. Please feel free to drop me an email with your CV!
hanson[dot]{last_name}[at]connect[dot]polyu[dot]hk
📰 Highlights
📜[2025.10] ✨Our Youtu-GraphRAG has been admitted by the DeepSeek Official Integrations.
📜[2025.09] ✨We have released the Youtu-GraphRAG that vertically unifies the GraphRAG framework for advanced industrial implementation and also an anonymous dataset named ‘AnonyRAG’.
📜[2025.06] We have released the first tailored benchmark for GraphRAG, GraphRAG-Bench and the corresponding leaderboard.
🚩[2025.05] I passed the Ph.D. oral defense! Thanks to my distinguished panel members: Prof.Yuanqing Zheng(PolyU), Prof. Yangqiu Song (HKUST), Prof. Yixin Cao (FDU)
🚩[2025.04] I will join `Qingyun’ Top Talent Program (腾讯青云计划) at Tencent Youtu Lab.
🚩[2025.02] I am nominated by both the Department of Computing and the Faculty of Computer and Mathematical Science as the ‘Best Research Postgraduate Student’ of 2024.
🚩[2023.04] I passed the confirmation as a Ph.D. Candidate. Thanks to the distinguished panel members: Prof. Qing Li, Prof. Song Guo and Dr. Bo Li.
🏆 Awards
2025 Best Research Postgraduate Student nominated by the Department of Computing in PolyU and Faculty of Computer and Mathematical Sciences.
2025 Tencent ‘Qingyun’ Top Talent Program
2025 Ant Group ‘Ant Star’ Top Talent Program
2024 NeurIPS Scholar Award
2023 Hong Kong Polytechnic University Additional Top Conference Grant
🎙 Talks
🎈Youtu-GraphRAG v1.0
📣Tencent Youtu Lab
📻 Social Media
🎈Youtu-GraphRAG v1.0
📣机器之心, 📣Tencent Cloud, 📣Tencent Youtu Lab, 📣老刘说NLP
🎈GraphRAG-Bench
📣NebulaGraph Tech Community, 📣Tencent Youtu Lab, 📣老刘说NLP
✍ Services
Program Committee Member
AAAI 2026, NeurIPS(2024-2025), ICML 2025, ICLR (2025-2026), ACL 2025 (Feb/May/Jul/Oct), TheWebConf(WWW) (2024-2026)
Selected Publications (first, co-first, corresponding)
*for co-first author, 📩 for corresponding author
1. Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning.
Junnan Dong* , Siyu An*, Yifei Yu, Qian-wen Zhang, Linhao Luo, Xiao Huang, Yunsheng Wu, Di Yin, Xing Sun
arxiv 
2. Cost-efficient Knowledge-based Question Answering with Large Language Models.
Junnan Dong, Qinggang Zhang, Chuang Zhou, Hao Chen, Daochen Zha, Xiao Huang
NeurIPS 2024
3. Modality-Aware Integration with Large Language Models for Knowledge-based VQA.
Junnan Dong* , Qinggang Zhang*, Huachi Zhou, Daochen Zha, Pai Zheng, Xiao Huang
ACL main 2024
4. Hierarchy-Aware Multi-Hop Question Answering over Knowledge Graphs.
Junnan Dong* , Qinggang Zhang*, Xiao Huang, Keyu Duan, Qiaoyu Tan, Zhimeng Jiang
WWW 2023
5. Active Ensemble Learning for Knowledge Graph Error Detection.
Junnan Dong, Qinggang Zhang, Xiao Huang, Qiaoyu Tan, Daochen Zha, Zihao Zhao
WSDM 2023
6. CLR-Bench: Evaluating Large Language Models in College-level Reasoning.
Junnan Dong, Zijin Hong, Yuanchen Bei, Feiran Huang, Xinrun Wang, Xiao Huang
arXiv
7. GraphRAG-Bench: Challenging Domain-Specific Reasoning for Graph Retrieval-Augmented Generation.
Yilin Xiao*, Junnan Dong*📩, Chuang Zhou, Su Dong, Qian-wen Zhang, Di Yin, Xing Sun, Xiao Huang
arxiv
8. HyperRAG: Query-centric Graph Retrieval-Augmented Generation with Hyperbolic Structuring.
Chuang Zhou, Junnan Dong📩, Yilin Xiao, Su Dong, Shengyuan Chen, Di Yin, Xiao Huang
arxiv
9. KnowGPT: Knowledge Graph Prompting for Large Language Models.
Qinggang Zhang*, Junnan Dong* , Hao Chen, Xiao Huang, Daochen Zha, Zailiang Yu
NeurIPS 2024