About me
My name is pronounced as “tyen-how pung”. I am a Ph.D. student (2021.09 - present) at the State Key Laboratory of Complex & Critical Software Environment and School of Computer Science and Engineering (SCSE), Beihang University, Beijing, China, supervised by Prof. Wenjun Wu. Before that, I obtained my BSc degree in 2020 from Beihang University (Awarded Outstanding Graduate & Honor Student).
Email: pengtianhao@buaa.edu.cn $\vert$ Google Scholar $\vert$ Github
Research Interests
I am interested in Graph Data Mining and Large Language Models, pursuing innovative solutions in both areas. Currently, my research focuses on the following areas:
- Large Language Models: Building and training large models to enhance reasoning abilities and explore the boundaries of their capabilities.
- Graph Data Mining: Developing efficient, scalable GNN models to process diverse graph types and represent complex network relationships.
News
- July 2025: Co-first author on two new papers released on ArXiv: a comprehensive survey on latent reasoning and a study on LLM-based agents leveraging cross-domain experience.
- June 2025: Contributed to a paper on an empirical study of building effective agents, released on ArXiv.
- January 2025: First author on a paper focusing on Contrastive Learning in Recommendation Systems, accepted by TKDE journal (IEEE Transactions on Knowledge and Data Engineering).
- December 2024: First author on a paper exploring Graph Contrastive Learning, accepted by AAAI 2025.
- November 2024: Co-authored a paper on Learning-to-Rank, accepted by KDD 2025.
- May 2024: Co-authored a paper on knowledge-based VQA for LLM, accepted by ACL 2024.
- April 2024: Co-authored a paper on EEG-based emotion classification, accepted by JNE (Journal of Neural Engineering).
- March 2024: Co-authored a paper on knowledge tracing, accepted by TOIS journal (ACM Transactions on Information Systems).
- December 2023: First author on a paper detailing heterophilic graph neural networks, accepted by ICDE 2024.
- February 2023: First author on a paper on Graph Transformer, accepted by AAAI 2023.
Publications
* indicates equal contribution.
Large Language Models
- A Survey on Latent Reasoning. [Paper]
Rui-Jie Zhu*, Tianhao Peng*, Tianhao Cheng*, Xingwei Qu*, Jinfa Huang, Dawei Zhu, Hao Wang, Kaiwen Xue, Xuanliang Zhang, Yong Shan, Tianle Cai, Taylor Kergan, Assel Kembay, Andrew Smith, Chenghua Lin, Binh Nguyen, Yuqi Pan, Yuhong Chou, Zefan Cai, Zhenhe Wu, Yongchi Zhao, Tianyu Liu, Jian Yang, Wangchunshu Zhou, Chujie Zheng, Chongxuan Li, Yuyin Zhou, Zhoujun Li, Zhaoxiang Zhang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Jason Eshraghian
ArXiv. - Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving. [Paper]
Xiangru Tang*, Tianrui Qin*, Tianhao Peng*, Ziyang Zhou, Daniel Shao, Tingting Du, Xinming Wei, Peng Xia, Fang Wu, He Zhu, Ge Zhang, Jiaheng Liu, Xingyao Wang, Sirui Hong, Chenglin Wu, Hao Cheng, Chi Wang, Wangchunshu Zhou
ArXiv. - OAgents: An Empirical Study of Building Effective Agents. [Paper]
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Yi Yao, Hanhao Li, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Xiaowan Li, Yuhui Liu, Yuchen Eleanor Jiang, Jun Wang, Changwang Zhang, Xiangru Tang, Ge Zhang, Jian Yang, Minghao Liu, Xitong Gao, Jiaheng Liu, Wangchunshu Zhou
ArXiv. - Soft Knowledge Prompt: Help External Knowledge Become a Better Teacher to Instruct LLM in Knowledge-based VQA. [Paper]
Qunbo Wang, Ruyi Ji, Tianhao Peng, Wenjun Wu, Zechao Li, Jing Liu
ACL 2024 (long paper), CCF-A.
Graph Data Mining
- TagRec: Temporal-Aware Graph Contrastive Learning with Theoretical Augmentation for Sequential Recommendation. [Paper]
Tianhao Peng, Haitao Yuan, Yongqi Zhang, Yuchen Li, Peihong Dai, Qunbo Wang, Senzhang Wang, Wenjun Wu
TKDE (IEEE Transactions on Knowledge and Data Engineering) 2025, CCF-A. - SOLA-GCL: Subgraph-oriented Learnable Augmentation Method for Graph Contrastive Learning. [Paper]
Tianhao Peng, Xuhong Li, Haitao Yuan, Yuchen Li, Haoyi Xiong
AAAI 2025, CCF-A. - GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy. [Paper]
Tianhao Peng, Wenjun Wu, Haitao Yuan, Zhifeng Bao, Zhao Pengrui, Xin Yu, Xuetao Lin, Yu Liang, Yanjun Pu
ICDE 2024, CCF-A. - CLGT: A Graph Transformer for Student Performance Prediction in Collaborative Learning. [Paper]
Tianhao Peng, Yu Liang, Wenjun Wu, Jian Ren, Zhao Pengrui, Yanjun Pu
AAAI 2023 - Pre-trained Molecular Language Models with Random Functional Group Masking. [Paper]
Tianhao Peng, Yuchen Li, Xuhong Li, Jiang Bian, Zeke Xie, Ning Sui, Shahid Mumtaz, Yanwu Xu, Linghe Kong, Haoyi Xiong
npj Artificial Intelligence 2025
Cross-Domain Applications
- ELAKT: Enhancing Locality for Attentive Knowledge Tracing. [Paper]
Yanjun Pu, Fang Liu, Rongye Shi, Haitao Yuan, Ruibo Chen, Tianhao Peng, Wenjun Wu
TOIS (ACM Transactions on Information System), CCF-A. - RankElectra: Semi-supervised Pre-training of Learning-to-Rank Electra for Web-scale Search. [Paper]
Yuchen Li, Haoyi Xiong, Yongqi Zhang, Jiang Bian, Tianhao Peng, Xuhong Li, Shuaiqiang Wang, Linghe Kong, Dawei Yin
KDD 2025, CCF-A. - FetchEEG: a hybrid approach combining feature extraction and temporal-channel joint attention for EEG-based emotion classification. [Paper]
Yu Liang, Chenlong Zhang, Shan An, Zaitian Wang, Kaize Shi, Tianhao Peng, Yuqing Ma, Xiaoyang Xie, Jian He and Kun Zheng
Journal of Neural Engineering
Research achievements
- [China national standard] I am one of the drafters of the China national standard "Information technology- Artificial intelligence- Code of practice for data annotation of machine learning".
- [China group standard] I am one of the drafters of the China group standard "Framework for intelligent microservices adaptation".
- [China group standard] I am one of the drafters of the China group standard "Intelligent microservices adaptation performance evaluation index system".
- [China patent] I am one of the drafters of the China patent "Code quality problem detection and repair method for continuous integration of microservices".
Services
- Journal Reviewers of TKDE, TLT, Applied Intelligence, Pattern Analysis and Applications
- Conference Reviewers of WWW, ACL, KDD, NeurIPS, AAAI