Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning

arXiv:2611.05942 · cs.LG · Submitted 2026-11-04 · Read on arXiv

cs.LG

Submitted: 2026-11-04

Updated: 2026-11-06

Code: https://github.com/Qwen-Applications/RewardBudget

Terminology

Sources

Related papers