Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards
cs.LG
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/huggingface/Math-Verify
Terminology
Sources
- Concise Reasoning via Reinforcement Learning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Large-Scale Data Selection for Instruction Tuning
- OpenAI o1 System Card
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Learning Robust Reasoning through Guided Adversarial Self-Play
- LIMR: Less is More for RL Scaling
- Understanding R1-Zero-Like Training: A Critical Perspective
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reinforcement Learning for Reasoning in Large Language Models with One Training Example
- A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret
- Evaluating the Performance of Large Language Models on GAOKAO Benchmark
- Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
- Consolidating Rewarded Perturbations for LLM 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