Cover Image

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Xuexiang, Yu, Hang, Zhu, Linchao, Wang, Gaoang
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Partial Policy Gradients for RL in LLMs
by: Mathur, Puneet, et al.
Published: (2026)

GradientStabilizer:Fix the Norm, Not the Gradient
by: Huang, Tianjin, et al.
Published: (2025)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
by: Pavlenko, Kirill, et al.
Published: (2026)

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
by: Helff, Lukas, et al.
Published: (2026)

Imbalanced Gradients in RL Post-Training of Multi-Task LLMs
by: Wu, Runzhe, et al.
Published: (2025)

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards
by: Li, Ming, et al.
Published: (2025)

GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
by: Xu, Haofeng, et al.
Published: (2026)

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling
by: Li, Derek, et al.
Published: (2025)

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

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
by: Cai, Xin-Qiang, 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)

Reward Hacking Mitigation using Verifiable Composite Rewards
by: Tarek, Mirza Farhan Bin, et al.
Published: (2025)

Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
by: Muslimani, Calarina, et al.
Published: (2025)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
by: Cho, Dongkyu Derek, et al.
Published: (2025)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
by: Cai, Xin-Qiang, et al.
Published: (2026)

BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
by: Hage, Tarjei Paule, et al.
Published: (2026)

Verifying Meta-Awareness via Predictive Rewards in Reasoning Models
by: Kim, Yoonjeon, et al.
Published: (2025)

Intrinsic Reward Policy Optimization for Sparse-Reward Environments
by: Cho, Minjae, et al.
Published: (2026)

Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping
by: Nazir, Mohammad Saif, et al.
Published: (2025)

Online Finetuning Decision Transformers with Pure RL Gradients
by: Luo, Junkai, et al.
Published: (2026)

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
by: Pan, Teng, et al.
Published: (2026)

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance
by: Yan, Kai, et al.
Published: (2026)

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
by: Salimi, Moein, et al.
Published: (2026)

On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL
by: Belcamino, Valerio, et al.
Published: (2026)

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
by: Chen, Fan, et al.
Published: (2022)

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

RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training
by: Ren, Tao, et al.
Published: (2025)

Incentivizing LLMs to Self-Verify Their Answers
by: Zhang, Fuxiang, et al.
Published: (2025)

An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
by: Plesner, Andreas, et al.
Published: (2026)

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
by: Zhao, Yang, et al.
Published: (2026)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
by: Wei, Zhepei, et al.
Published: (2025)

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
by: Ye, Chenlu, et al.
Published: (2025)

Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning
by: Nguyen, Viet Bac, et al.
Published: (2026)

Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation
by: Duan, Xintong, et al.
Published: (2025)

COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management
by: Gross, Dennis
Published: (2026)

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
by: Roth, Amit, et al.
Published: (2026)

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
by: He, Haoran, et al.
Published: (2025)

Entropy Centroids as Intrinsic Rewards for Test-Time Scaling
by: Zhao, Wenshuo, 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)