Cover Image

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Haoran, Ye, Yuxiao, Cai, Qingpeng, Hu, Chen, Jiao, Binxing, Jiang, Daxin, Pan, Ling
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning
by: Yang, Zhaohui, et al.
Published: (2025)

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

Random Policy Evaluation Uncovers Policies of Generative Flow Networks
by: He, Haoran, et al.
Published: (2024)

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

SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
by: Lin, Jiaye, et al.
Published: (2025)

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
by: Yang, Yuxiao, et al.
Published: (2026)

GARDO: Reinforcing Diffusion Models without Reward Hacking
by: He, Haoran, et al.
Published: (2025)

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

CaRT: Teaching LLM Agents to Know When They Know Enough
by: Liu, Grace, et al.
Published: (2025)

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

State Regularized Policy Optimization on Data with Dynamics Shift
by: Xue, Zhenghai, et al.
Published: (2023)

Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
by: Zhang, Yeqin, et al.
Published: (2025)

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
by: Zhang, Zijing, et al.
Published: (2025)

Escaping the Verifier: Learning to Reason via Demonstrations
by: Cai, Locke, et al.
Published: (2025)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
by: Zhai, Zhiyuan, et al.
Published: (2026)

Boosting LLM Reasoning via Human-Inspired Reward Shaping
by: Lin, Wenze, et al.
Published: (2026)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
by: Ma, Zhengzhao, et al.
Published: (2026)

DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
by: Li, Gang, et al.
Published: (2025)

On Designing Effective RL Reward at Training Time for LLM Reasoning
by: Gao, Jiaxuan, et al.
Published: (2024)

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

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

From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs
by: Wang, Xiaoxuan, et al.
Published: (2025)

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

Reward Is Enough: LLMs Are In-Context Reinforcement Learners
by: Song, Kefan, et al.
Published: (2025)

Trade-R1: Bridging Verifiable Rewards to Stochastic Environments via Process-Level Reasoning Verification
by: Sun, Rui, et al.
Published: (2026)

Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
by: Sharma, Aman, et al.
Published: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
by: Liu, Yixin, et al.
Published: (2026)

Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
by: Bai, Bizhe, et al.
Published: (2026)

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

Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning
by: Yang, Zhaohui, et al.
Published: (2025)

ReDit: Reward Dithering for Improved LLM Policy Optimization
by: Wei, Chenxing, et al.
Published: (2025)

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

LLM Reasoning with Process Rewards for Outcome-Guided Steps
by: Rezaei, Mohammad, et al.
Published: (2026)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
by: Yue, Chuhuai, et al.
Published: (2025)

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

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

FlowRL: Matching Reward Distributions for LLM Reasoning
by: Zhu, Xuekai, et al.
Published: (2025)

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
by: Jiang, Yuhua, et al.
Published: (2025)

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
by: Jiang, Xitai, et al.
Published: (2026)

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