Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- The Llama 3 Herd of Models
- Reinforced Self-Training (ReST) for Language Modeling
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
- You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Survey on Self-Evolution of Large Language Models
- Self-Taught Evaluators
- On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
- Qwen3 Technical Report
- No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
- Group Sequence Policy Optimization
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks