Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR
cs.LG, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- Tutorial on amortized optimization
- Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
- Rethinking On-Policy Self-Distillation for Thinking Models
- Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
- RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
- POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- HybridFlow: A Flexible and Efficient RLHF Framework
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Qwen3 Technical Report
- Self-Distilled RLVR
- What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret
- VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
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