SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation
cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/Yueeeeeeee/SIPO
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization
- Measuring Mathematical Problem Solving With the MATH Dataset
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Reinforcement Learning via Self-Distillation
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Understanding R1-Zero-Like Training: A Critical Perspective
- Olmo 3
- RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- OpenAI GPT-5 System Card
Related papers
- 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
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection