Papers

Group Entropy-Controlled Policy Optimization

24 upvotes · 18 JUL 2026 · Guangran Cheng, Chengqi Lyu, Songyang Gao et al.

This paper proposes a new method for reinforcement learning in large language models, called Group Entropy-Controlled Policy Optimization (GEPO), which helps balance exploration and exploitation by controlling entropy levels across different tasks. Practitioners might care about GEPO because it can lead to more balanced and task-specific exploration levels.

reinforcement learning large language models entropy control group policy optimization asymmetric advantage shaping

Browse by term

Matching papers

Group Entropy-Controlled Policy Optimization