CERO: Where and When to Allocate Rollouts for RL Post-Training

cs.LG, cs.AI

Submitted: 2026-10-07

Updated: 2026-10-07

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Self-Evolving Curriculum for LLM Reasoning
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
• Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning
• Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training
• Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
• CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
• Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
• Qwen2.5 Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
• Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
• Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
• Qwen3 Technical Report
• CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning
• Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
• Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks