Boosting LLM Exploration via Weak-Model Guidance in RLVR
By Xingyu Shen · Paper · cs.CL
Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves LLM reasoning but often causes a drop in policy entropy, leading to narrowed reasoning coverage and degraded pass@$k$ for large $k$. While existing methods mitigate this entropy collapse through algorith