Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Rethinking Entropy Regularization in Large Reasoning Models
- Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
- Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
- RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
- Qwen3 Technical Report
- Heterogeneous Agent Collaborative Reinforcement Learning
- Group Sequence Policy Optimization
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks