EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Xingjian Zhang, Siwei Wen, wenjun wu, Lei Huang

Keywords: Large Language Models, Reasoning

Abstract: Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often encounters the issue of identical rewards within groups, leading to the advantage collapse problem. Existing works typically address this challenge from two perspectives: enforcing model reflection to enhance response diversity, and introducing internal feedback to augment the training signal (advantage). In this work, we begin by analyzing the limitations of model reflection and investigating the policy entropy of responses at the fine-grained sample level. Based on our experimental findings, we propose the EDGE-GRPO algorithm, which adopts Entropy-Driven Advantage and Guided Error Correction to effectively mitigate the problem of advantage collapse. Extensive experiments on different models across multiple main reasoning benchmarks demonstrate the effectiveness and superiority of our approach. The code and weights will be released upon acceptance to facilitate further research in this field.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 9009