The Race Is Decided Early! A Kernel Law Predicts Lock-In in Majority-Vote Test-Time RL
cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
- Collective Dynamics of Self-Reinforcement: How Cross-Task Coupling Drives Policy Collapse in Unsupervised RLVR
- Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning
- The Llama 3 Herd of Models
- Tool Verification for Test-Time Reinforcement Learning
- Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting
- CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning
- Maximizing Confidence Alone Improves Reasoning
- Can Large Reasoning Models Self-Train?
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Learning Dynamics in RL Post-Training for Language Models
- Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
- Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL
- Qwen2.5 Technical Report
- Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
- Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
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