XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of rollouts stabilizes training, existing approaches suffer from limited exploration on challenging prompts and leave informative feedback signals underexploited, due to context-independent rollout allocation across prompts (e.g., generating 16 rollouts per prompt) and relying heavily on sparse rewards. This paper presents XRPO(eXplore - eXploit GRPO), a unified framework that recasts policy optimization through the principled lens of rollout exploration-exploitation. To enhance exploration, XRPO introduces a mathematically grounded rollout allocator that adaptively prioritizes prompts with higher potential for uncertainty reduction. It further addresses stagnation on zero-reward prompts through an in-context seeding strategy that injects curated exemplars, steering the model into more difficult reasoning trajectories. To strengthen exploitation, XRPO develops a group-relative, novelty-aware advantage sharpening mechanism that leverages sequence likelihoods to amplify low-probability yet correct responses, thereby extending the policy's reach beyond sparse rewards. Experiments across diverse math and coding benchmarks on both reasoning and non-reasoning models demonstrate that XRPO outperforms existing advances (e.g., GRPO and GSPO) up to 4% pass@1 and 6% cons@32, while accelerating training convergence by up to 2.7X.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Targeted Exploration via Unified Entropy Control for Reinforcement Learning
Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO…
Reinforcement LearningManifold-Aware Exploration for Reinforcement Learning in Video Generation
Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex…
Reinforcement LearningVideo GenerationParameter Exploration for RLVR via Variational Learning
Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcement learning recipes that can significan…
Mathematical ReasoningReinforcement LearningCode GenerationToken Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open probl…
Reinforcement LearningSmaller Models are Natural Explorers for Policy-Level Diversity in GRPO
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies primarily increase diversity by injecting mo…
Mathematical Reasoning