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:2609.37898v1 Announce Type: new Abstract: Reinforcement learning for long-horizon agents typically relies on sparse outcome-based rewards. This leads to a severe cold-start problem, as early-st...
arXiv:2606. 15912v1 Announce Type: cross Abstract: Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice.
arXiv:2609.36642v1 Announce Type: new Abstract: Language-model agents are usually trained by reinforcement learning from one reward per episode, and privileged self-distillation enriches it by lettin...
arXiv:2606. 27814v4 Announce Type: replace Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.
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.
The paper examines on‑policy self‑distillation (OPSD) for multi‑turn agents, showing that using privileged information (PI) in the loss can make agents appear confident yet underperform plain RL, sometimes worse than the untrained base model. To address this, the authors propose Privileged Self‑Practice (PSP), which keeps PI in the prompt and uses it only during sampling, not in the loss. PSP consistently outperforms plain GRPO across AppWorld and SWE‑bench Verified, improving task‑goal completion by up to 65% and resolved rate by up to 61%.
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.
arXiv:2609.14636v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a standard approach for transferring capabilities from large teachers to compact students. Its cost, however, i...
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach.
arXiv:2609.37132v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves large language models by letting a self-teacher with privileged information provide dense token-level super...
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63. 0-68.
arXiv:2606. 27814v1 Announce Type: new Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.