RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning
cs.LG, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/THUDM/slime
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
- Soft Adaptive Policy Optimization
- RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-V3 Technical Report
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
- HybridFlow: A Flexible and Efficient RLHF Framework
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
- MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Group Sequence Policy Optimization
- Optimizing RLHF Training for Large Language Models with Stage Fusion
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