# DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management

arXiv: https://arxiv.org/abs/2505.12951 · HTML: https://mlsanity.com/paper/2505.12951/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)
- [Equivalence Between Policy Gradients and Soft Q-Learning](https://mlsanity.com/paper/1704.06440/) (2017)
- [Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems](https://mlsanity.com/paper/2412.09413/) (2024)
- [Generalized Preference Optimization: A Unified Approach to Offline Alignment](https://mlsanity.com/paper/2402.05749/) (2024)
- [On Memorization of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2410.23123/) (2024)
- [Mirror Descent Policy Optimization](https://mlsanity.com/paper/2005.09814/) (2020)
- [CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models](https://mlsanity.com/paper/2503.22342/) (2025)
- [T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling](https://mlsanity.com/paper/2501.11651/) (2025)
- [Reinforcement Learning with a Corrupted Reward Channel](https://mlsanity.com/paper/1705.08417/) (2017)
- [Offline Regularised Reinforcement Learning for Large Language Models Alignment](https://mlsanity.com/paper/2405.19107/) (2024)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [Vanishing Gradients in Reinforcement Finetuning of Language Models](https://mlsanity.com/paper/2310.20703/) (2023)
- [Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage](https://mlsanity.com/paper/2310.18434/) (2023)
- [Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning](https://mlsanity.com/paper/2504.04524/) (2025)

## Built on by (most cited first, 1 of 1)

- [CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning](https://mlsanity.com/paper/2608.03068/) (2026)

## Abstract (arXiv)

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches usually rely on handcrafted rule-based reward functions. However, the tarde-offs of exploration and exploitation in RL algorithms involves multiple complex considerations, and the theoretical and empirical impacts of manually designed reward functions remain insufficiently explored. In this paper, we propose Decoupled Group Reward Optimization (DGRO), a general RL algorithm for LLM reasoning. On the one hand, DGRO decouples the traditional regularization coefficient into two independent hyperparameters: one scales the policy gradient term, and the other regulates the distance from the sampling policy. This decoupling not only enables precise control over balancing exploration and exploitation, but also can be seamlessly extended to Online Policy Mirror Descent (OPMD) algorithms in Kimi k1.5 and Direct Reward Optimization. On the other hand, we observe that reward variance significantly affects both convergence speed and final model performance. We conduct both theoretical analysis and extensive empirical validation to assess DGRO, including a detailed ablation study that investigates its performance and optimization dynamics. Experimental results show that DGRO achieves state-of-the-art performance on the Logic dataset with an average accuracy of 96.9%, and demonstrates strong generalization across mathematical benchmarks.