Zhenyu Hou

Zhenyu Hou

Language Model; Agent; Reinforcement Learning. My recent work centers on post-training for reasoning and alignment.

GLM-5: from Vibe Coding to Agentic Engineering

Published in arXiv, 2026

This technical report introduces GLM-5 and details its training, agentic reasoning/coding performance, and reinforcement-learning infrastructure.

Recommended citation: 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.
Download Paper