Margin-Guided Token Credit for Reinforcement Learning with Verifiable Rewards
cs.LG, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/huggingface/Math-Verify
Terminology
Sources
- The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Forking Paths in Neural Text Generation
- Evaluating Large Language Models Trained on Code
- Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
- Reasoning with Exploration: An Entropy Perspective
- Process Reinforcement through Implicit Rewards
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- Concise Reasoning via Reinforcement Learning
- Deep Think with Confidence
- Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
- A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
- Language Models (Mostly) Know What They Know
- Scalable Best-of-N Selection for Large Language Models via Self-Certainty
- VinePPO: Refining Credit Assignment in RL Training of LLMs
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis