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

• URL: http://arxiv.org/abs/2505.12951v1
• Date: Mon, 19 May 2025 10:44:49 GMT
• Title: DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management
• Authors: Xuerui Su, Liya Guo, Yue Wang, Yi Zhu, Zhiming Ma, Zun Wang, Yuting Liu,
• Abstract summary: Decoupled Group Reward Optimization (DGRO) is a general RL algorithm for Large Language Models (LLMs) reasoning.<n>We 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.
• Score: 18.953750405635393
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [86.30192066451256]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training [121.5858973157225]
  We investigate the effects of prolonged reinforcement learning on a small language model across a diverse set of reasoning domains.<n>We introduce controlled KL regularization, clipping ratio, and periodic reference policy resets as critical components for unlocking long-term performance gains.<n>Our model achieves significant improvements over strong baselines, including +14.7% on math, +13.9% on coding, and +54.8% on logic puzzle tasks.
  arXiv  Detail & Related papers  (2025-07-16T17:59:24Z)
• Reasoning with Exploration: An Entropy Perspective on Reinforcement Learning for LLMs [112.40801692473723]
  Balancing exploration and exploitation is a central goal in reinforcement learning (RL)<n>We introduce a minimal modification to standard RL with only one line of code: augmenting the advantage function with an entropy-based term.<n>Our method achieves significant gains on the Pass@K metric, even when evaluated with extremely large K values.
  arXiv  Detail & Related papers  (2025-06-17T17:54:03Z)
• Behavior Injection: Preparing Language Models for Reinforcement Learning [24.46625106928253]
  Reinforcement fine-tuning (RFT) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs)<n>LLMs can respond very inconsistently to RFT: some show substantial performance gains, while others plateau or even degrade.<n>We propose behavior injection, a task-agnostic data-augmentation scheme applied prior to RL.
  arXiv  Detail & Related papers  (2025-05-25T00:54:50Z)
• Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models [83.8639566087953]
  We propose a direct retrieval-augmented optimization framework, named DRO, that enables end-to-end training of two key components.<n>DRO alternates between two phases: (i) document permutation estimation and (ii) re-weighted, progressively improving RAG components.<n>Our theoretical analysis reveals that DRO is analogous to policy-gradient methods in reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-05T23:54:53Z)
• SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM [18.275547804539016]
  Two-Staged history-Resampling Policy optimization surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks.<n>We introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples.
  arXiv  Detail & Related papers  (2025-04-19T13:06:03Z)
• Towards General-Purpose Model-Free Reinforcement Learning [40.973429772093155]
  Reinforcement learning (RL) promises a framework for near-universal problem-solving.<n>In practice, RL algorithms are often tailored to specific benchmarks.<n>We propose a unifying model-free deep RL algorithm that can address a diverse class of domains and problem settings.
  arXiv  Detail & Related papers  (2025-01-27T15:36:37Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)
• Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning [24.09547181095033]
  Causal Graph is a structure built upon the relation between objects and events. We propose a framework with theoretical performance guarantees that alternates between two steps. Our performance improvement is attributed to the virtuous cycle of causal discovery, transition modeling, and policy training.
  arXiv  Detail & Related papers  (2022-07-19T05:31:16Z)
• Counterfactual Maximum Likelihood Estimation for Training Deep Networks [83.44219640437657]
  Deep learning models are prone to learning spurious correlations that should not be learned as predictive clues. We propose a causality-based training framework to reduce the spurious correlations caused by observable confounders. We conduct experiments on two real-world tasks: Natural Language Inference (NLI) and Image Captioning.
  arXiv  Detail & Related papers  (2021-06-07T17:47:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.