Author

Xin Shen

View on Semantic Scholar

1 paper indexed here

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.

#small language model Preprint Aug 2026

Boosting LLM Exploration via Weak-Model Guidance in RLVR

This work empirically study the potential of outer prefixes, revealing the mechanism of the impact of distributional discrepancy to the exploration dynamics in RLVR training and efficiently mitigates entropy collapse without requiring additional SFT, intricate reward designs, or complex prompting.

Xin Shen, Hui-Shuai Zhang, Peng Li et al. · 0 citations