Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
cs.LG
Submitted: 2026-05-08
Updated: 2026-10-28
Comments: 25 pages, 10 figures, 8 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
- Measuring Mathematical Problem Solving With the MATH Dataset
- Understanding R1-Zero-Like Training: A Critical Perspective
- Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
- HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs
- Code Comprehension then Auditing for Unsupervised LLM Evaluation
- Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
- The Invisible Leash: Why RLVR May or May Not Escape Its Origin
- Qwen2.5 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
- SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
- Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
- The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
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