Test-Time Self-Play: Scaling without a Verifier
cs.LG, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Phi-4 Technical Report
- The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
- Test-time Offline Reinforcement Learning on Goal-related Experience
- Scaling Self-Play with Self-Guidance
- Dota 2 with Large Scale Deep Reinforcement Learning
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Towards Understanding Self-play for LLM Reasoning
- Self-Questioning Language Models
- Self-Evolving Curriculum for LLM Reasoning
- Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning
- Reinforced Self-Training (ReST) for Language Modeling
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- R-Zero: Self-Evolving Reasoning LLM from Zero Data
- Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Language Self-Play For Data-Free Training
- Majority Voting for Code Generation
- Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
- Can Large Reasoning Models Self-Train?
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