On the Reliability of Majority-Vote Pseudo-Labels in Test-Time Reinforcement Learning
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- How Far Can Unsupervised RLVR Scale LLM Training?
- Measuring Mathematical Problem Solving With the MATH Dataset
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins
- ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
- Training language models to follow instructions with human feedback
- Iterative Reasoning Preference Optimization
- Maximizing Confidence Alone Improves Reasoning
- Qwen2.5 Technical Report
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Proximal Policy Optimization Algorithms
- Spurious Rewards: Rethinking Training Signals in RLVR
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
- Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents