Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
cs.LG, cs.AI
Submitted: 2026-06-17
Updated: 2026-10-08
Code: https://github.com/BITHLP/SC-GRPO
Terminology
Sources
- Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
- Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
- Process Reinforcement through Implicit Rewards
- HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
- On Designing Effective RL Reward at Training Time for LLM Reasoning
- JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
- Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
- Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
- Distilling the Knowledge in a Neural Network
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Reinforcement Learning via Self-Distillation
- Adversarial Training for Process Reward Models
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- DocOS: Towards Proactive Document-Guided Actions in GUI Agents
- Self-Distillation Enables Continual Learning
- Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Self-Distilled RLVR
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks