EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- OpenThoughts: Data Recipes for Reasoning Models
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
- EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
- On-Policy Self-Distillation without Any Supervision
- Visual-Advantage On-Policy Distillation for Vision-Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OpenAI GPT-5 System Card
- SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
- Qwen3 Technical Report
- Self-Distilled RLVR
- Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation
- Latent On-Policy Self-Distillation
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
- ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation
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