Author

Jiaqiang Tang

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Predictive Divergence Masks for LLM RL

The predictive divergence mask is proposed, which asks whether the next policy-gradient step will increase or decrease the same divergence used by the trust region, and the resulting masks improve RL training across model scales and precision settings.

Xiang-Xin Zhou, Jiarui Yao, Penghui Qi et al. · arXiv.org · 0 citations