Cunxiang Wang(@CunxiangWang):GLM-5.2 is not only stronger on benchmarks, but also much better in real app development scenarios — iOS, Android, WeChat Mini Programs, and more. Behind this jump is a full loop from environment construction, evaluation, data optimization, reward design, to training. Real tasks, real execution, real improvement.

Cunxiang Wang

@CunxiangWang

Researcher @Zai_org, Postdoc @thukeg, working with @jietang. Core contributor to GLM series. Focusing on real long-horizon agentic tasks, self-evolving LLMs

Joined August 2019

1.3K Following 2K Followers

Cunxiang Wang@CunxiangWang

2026.06.19 03:12

GLM-5.2 is not only stronger on benchmarks, but also much better in real app development scenarios — iOS, Android, WeChat Mini Programs, and more. Behind this jump is a full loop from environment construction, evaluation, data optimization, reward design, to training. Real tasks, real execution, real improvement.

324

Forward to community

Most Popular Users