Cover Image

Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Mroueh, Youssef
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Information Theoretic Guarantees For Policy Alignment In Large Language Models
by: Mroueh, Youssef
Published: (2024)

Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models
by: Le, Khiem, et al.
Published: (2026)

Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
by: Wang, Longwen, et al.
Published: (2026)

Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards
by: Heckel, Reinhard, et al.
Published: (2026)

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
by: Cai, Xin-Qiang, et al.
Published: (2025)

Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
by: Zeng, Guanning, et al.
Published: (2025)

Guided Speculative Inference for Efficient Test-Time Alignment of LLMs
by: Geuter, Jonathan, et al.
Published: (2025)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
by: Lu, Xiaodong, et al.
Published: (2026)

KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
by: Aminian, Gholamali, et al.
Published: (2025)

CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
by: Mroueh, Youssef, et al.
Published: (2026)

Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs
by: Alam, Md Tanvirul, et al.
Published: (2026)

Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
by: Zhu, Yuxuan, et al.
Published: (2026)

Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward
by: Tang, Xinyu, et al.
Published: (2025)

Effective Reward Specification in Deep Reinforcement Learning
by: Roy, Julien
Published: (2024)

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
by: Gunjal, Anisha, et al.
Published: (2025)

Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data
by: Tang, Yunhao, et al.
Published: (2025)

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
by: Wang, Jingyi, et al.
Published: (2026)

VeriGate: Verifier-Gated Step-Level Supervision for GRPO
by: Agrawal, Aakriti, et al.
Published: (2026)

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
by: Huang, Runhui, et al.
Published: (2026)

Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening
by: He, Andre, et al.
Published: (2025)

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
by: Huang, Guanhua, et al.
Published: (2025)

Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
by: Yoon, Deokgyu, et al.
Published: (2026)

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
by: Hu, Haoyu, et al.
Published: (2026)

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
by: Zhang, Feng, et al.
Published: (2026)

DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay
by: Li, Long, et al.
Published: (2026)

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
by: Stojanovski, Zafir, et al.
Published: (2025)

Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
by: Nguyen, Hieu Trung, et al.
Published: (2026)

How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
by: Tian, Minghao, et al.
Published: (2026)

GRPO is Secretly a Process Reward Model
by: Sullivan, Michael, et al.
Published: (2025)

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
by: Aminian, Gholamali, et al.
Published: (2025)

The Implicit Curriculum: Learning Dynamics in RL with Verifiable Rewards
by: Huang, Yu, et al.
Published: (2026)

LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
by: Lai, Yao, et al.
Published: (2026)

Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
by: Zhang, Xin, et al.
Published: (2026)

Improving the Effectiveness of Potential-Based Reward Shaping in Reinforcement Learning
by: Müller, Henrik, et al.
Published: (2025)

Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
by: Rioux, Gabriel, et al.
Published: (2024)

Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments
by: de Oliveira, Bryan L. M., et al.
Published: (2025)

FairGRPO: Fair Reinforcement Learning for Equitable Clinical Reasoning
by: Dai, Shiqi, et al.
Published: (2025)

Graph-GRPO: Training Graph Flow Models with Reinforcement Learning
by: Zhu, Baoheng, et al.
Published: (2026)

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation
by: Zhu, Speed, et al.
Published: (2025)

Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
by: Ackermann, Johannes, et al.
Published: (2026)