arXiv:2606. 03532v1 Announce Type: cross Abstract: Self on-policy distillation trains a student policy against a teacher derived from its own parameter history, yet the teacher's update schedule -- which governs the \emph{temporal coupling} between teacher and student -- has not been systematically studied as a stability variable.
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...
arXiv:2608. 09447v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation.
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:2605. 11458v3 Announce Type: replace Abstract: On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution.
arXiv:2609.24646v1 Announce Type: new Abstract: On-policy self-distillation fine-tuning (SDFT) learns new skills from demonstrations while reducing forgetting, but it always distils toward the full d...
The paper introduces temporal self‑distillation for reinforcement learning with verifiable rewards (RLVR), proposing that a policy can learn from a stronger future checkpoint of itself. Two methods—Near‑Future Policy Optimization (NPO) and Near‑Future Policy Distillation (NPD)—use verified future‑self trajectories and token‑level transfer, respectively, while AutoNPO adaptively selects the optimal future checkpoint. Experiments on eight image‑text benchmarks show that near‑future teachers yield higher performance than far‑future ones, indicating that the balance between new capability and learner compatibility is key.
The paper presents a causal analysis of a compressed VLA policy that performs well in offline tests but fails in closed‑loop execution on a simulated pick‑and‑place task. An 8‑layer distillation of Octo‑Base retains most parameters and passes all offline metrics, yet collapses during deployment, with early stages degrading gradually and final transport failing entirely. The failure is traced to a negative, late‑heavy residual in the action trace, and standard remedies (continued training, offline data, command‑level compensation, clamping) do not restore performance; only a minimal‑pair intervention that mixes deployment‑distribution rollouts with teacher data restores parity with the teacher. whyItMatters":"The study demonstrates that offline validation metrics alone are insufficient to guarantee closed‑loop success for compressed policies, highlighting the need for targeted deployment‑time testing and interventions."
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:2607. 18293v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts.
The paper introduces Regularized Emphatic Temporal‑Difference Learning (RETD), a modification of ETD that normalizes the post‑shock dynamics while preserving the emphatic TD signal and importance ratios. RETD achieves almost‑sure convergence under harmonic diminishing stepsizes and provides a conditional constant‑stepsize moment‑contraction guarantee, demonstrating negative Lyapunov exponents on a two‑state counterexample and the Baird point. Extensive experiments confirm RETD’s ability to recover the ETD fixed point, exhibit a non‑monotone stability region, and maintain task‑dependent performance.
The paper investigates self‑distillation techniques for language models by systematically varying three key design choices: the source of rollout tokens (student vs. teacher), the teacher coupling strategy (frozen or exponential moving average), and the KL divergence direction (reverse or forward). Experiments on Qwen2.5‑7B and Ministral‑3‑3B across 1,200 adaptation runs reveal that rollout source mainly affects acquisition on contradictory tasks, teacher coupling most strongly influences acquisition across all tasks, and KL direction impacts retention differently depending on the model. A controlled theoretical model reproduces these empirical trends, offering a unified framework for understanding acquisition‑retention trade‑offs in self‑distillation.
arXiv:2609. 40285v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories.