All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- Phi-4-reasoning Technical Report
- M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- Soft Adaptive Policy Optimization
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Skywork Open Reasoner 1 Technical Report
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Let's Verify Step by Step
- Understanding R1-Zero-Like Training: A Critical Perspective
- The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- Kimi K3: Open Frontier Intelligence
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
- Qwen3 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Understanding Diversity Collapse in RLVR via the Lens of Overtraining
- VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
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