Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
cs.CL
Submitted: 2025-07-21
Updated: 2026-11-07
Code: https://github.com/huggingface/Math-Verify
Terminology
Sources
- The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
- Reasoning with Exploration: An Entropy Perspective
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
- Process Reinforcement through Implicit Rewards
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- Skywork Open Reasoner 1 Technical Report
- Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
- Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
- Understanding R1-Zero-Like Training: A Critical Perspective
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
- Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
- Qwen3 Technical Report
- VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data