arXiv Machine Learning
PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 5
Agentic Reinforcement Learning with Self-Distilled Reward Shaping
arXiv:2608. 03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.
arXiv Machine Learning
Jul 22
H$^2$SD: Hybrid Hindsight Self-Distillation
arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.
arXiv AI
Sep 18
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
RetireOPD introduces a self-retiring on‑policy distillation method for agentic reinforcement learning. It first trains a skill‑conditioned teacher with environment rewards, then jointly trains a skill‑free student with RL and OPD, allowing the student to autonomously stop using the teacher when its performance aligns with the teacher’s. Experiments on Qwen2.5 models show significant gains in ALFWorld success rates and WebShop accuracy compared to RL baselines and the teacher itself.
arXiv AI
6d ago
From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents
The paper introduces Privileged Self-Practice (PSP), a method that retains privileged information (PI) in the prompt rather than the loss during on‑policy self‑distillation for multi‑turn agents. PSP injects short per‑task instructions from an analyzer model when rollouts fail, sampling again with the instruction in context and training with the unchanged GRPO objective. Experiments on AppWorld and SWE‑bench Verified show PSP consistently outperforms plain GRPO, boosting task‑goal completion by up to 65% and resolved rate by up to 61% across three student models.
arXiv AI
Aug 14
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv AI
Aug 6
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.