PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning

arXiv:2609.36642 · cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/balibata/PR-OPD

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes

Sources

• Understanding intermediate layers using linear classifier probes
• Verbalizable Representations Form a Global Workspace in Language Models
• Distilling the Knowledge in a Neural Network
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• Unifying distillation and privileged information
• Self-Distilled Agentic Reinforcement Learning
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
• PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
• Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents
• Privileged Information Distillation for Language Models
• Qwen2.5 Technical Report
• FitNets: Hints for Thin Deep Nets
• On the Geometry of On-Policy Distillation
• Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Learning by Distilling Context
• UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
• Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
• AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

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