Shenzhi-Wang / Beyond-the-80-20-Rule-RLVRLinks

The open-source code for the NeurIPS 2025 paper, "Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning."
25Updated this week

Alternatives and similar repositories for Beyond-the-80-20-Rule-RLVR

Users that are interested in Beyond-the-80-20-Rule-RLVR are comparing it to the libraries listed below

Sorting: