GLM-5: from Vibe Coding to Agentic Engineering
GLM-5 Team, Zeng, A., Lv, X., Hou, Z., Du, Z., Zheng, Q., Chen, B., Yin, D., Ge, C., et al. (2026). "GLM-5: from Vibe Coding to Agentic Engineering." arXiv:2602.15763.
CV
Education
- PhD in Computer Science and Technology, Tsinghua University, 2021–present
- BS in Computer Science and Technology, Tsinghua University, 2017–2021
Research interests
Language Model Agent and Reasoning; Reinforcement Learning; LLM Alignment; Self-Supervised Learning on Graphs
Experience
- GLM Team, Zhipu AI / Tsinghua University — Core Contributor
- Led post-training (RLHF/RL) for improved reasoning and alignment across the ChatGLM and GLM model families.
- Tech lead for the GLM-4.5 series; drove agentic, reasoning, and coding capability development.
- Drove LLM training/evaluation iterations for GLM-5 agentic engineering.
Open-source projects
- GraphMAE / GraphMAE2 — Self-supervised masked graph autoencoders (KDD 2022, WWW 2023)
- CogDL — Comprehensive library for graph deep learning (WWW 2023)
- AutoProNE — Automated unsupervised graph representation learning (TKDE 2021)
Skills
- Python, PyTorch
- Large language model training and RLHF
- Graph neural networks and representation learning
Publications
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Zhipu AI et al. (2025). "GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models." arXiv:2508.06471.
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Hu, W., Xu, C., Hou, Z., et al. (2025). "T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling." ICML.
Does RLHF Scale? Exploring the Impacts From Data, Model, and Method
Hou, Z., Du, P., Niu, Y., Du, Z., Zeng, A., Liu, X., Huang, M., Wang, H., Tang, J., and Dong, Y. (2025). "Does RLHF Scale? Exploring the Impacts From Data, Model, and Method." ICLR.
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., Hou, Z., and others. (2024). "ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools." arXiv:2406.12793.
ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
Hou, Z., Niu, Y., Du, Z., Zhang, X., Liu, X., Zeng, A., Zheng, Q., Huang, M., Wang, H., Tang, J., and Dong, Y. (2024). "ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback." arXiv:2404.00934.
Harnessing Large Language Models for Hyperedge Prediction
Hou, Z., Fang, Y., Liu, Z., Cen, Y., Zheng, V., and Tang, J. (2024). "Harnessing Large Language Models for Hyperedge Prediction." AAAI.
GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner
Hou, Z., et al. (2023). "GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner." WWW.
CogDL: A Comprehensive Library for Graph Deep Learning
Cen, Y., Hou, Z., Wang, Y., Chen, Q., Luo, Y., Yu, Z., et al. (2023). "CogDL: A Comprehensive Library for Graph Deep Learning." WWW.
MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis
Hou, Z., Cen, Y., Liu, Z., Wu, D., Wang, B., Li, X., Hong, L., and Tang, J. (2023). "MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis." AAAI.
GraphMAE: Self-Supervised Masked Graph Autoencoders
Hou, Z., Liu, X., Cen, Y., Dong, Y., Yang, H., Wang, C., and Tang, J. (2022). "GraphMAE: Self-Supervised Masked Graph Autoencoders." KDD.
Automated Unsupervised Graph Representation Learning
Hou, Z., Cen, Y., Dong, Y., Zhang, J., and Tang, J. (2021). "Automated Unsupervised Graph Representation Learning." IEEE TKDE.
Self-Supervised Attributed Graph Learning: A Comprehensive Review
Xie, Y., Xu, Z., Ji, J., Wang, Z., Wang, S., Liu, J., Ding, T., Hou, Z., and Tang, J. (2021). "Self-Supervised Attributed Graph Learning: A Comprehensive Review." IEEE TKDE.