The article discusses the challenge of teaching foundation models new skills without disrupting existing capabilities. It proposes a reinforcement learning-based method called on‑policy self‑distillation as a potential solution. The piece explores how this approach could transform post‑training processes for large language models.
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:2607. 01763v1 Announce Type: new Abstract: Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities.
arXiv:2606. 14368v1 Announce Type: new Abstract: We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve by tutoring each other through on-policy feedback.
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.
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.
arXiv:2601. 19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models.
arXiv:2609.08798v1 Announce Type: new Abstract: Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important...
The paper investigates how much training data is required for on‑policy distillation (OPD) of foundation models. It shows that in two single‑teacher settings, only eight real prompts can match the performance of 17,000 problems, and that 64 self‑generated questions can replace full external datasets. In multi‑teacher scenarios, 1,000 generated questions achieve comparable results to 7,000 real examples, while fully implicit question generation works only in limited cases.
The paper introduces SCOUT, a co‑training framework that adapts an off‑policy teacher to better continue from student‑generated prefixes in on‑policy distillation (OPD). By periodically optimizing the teacher’s conditional continuation ability using reinforcement learning with verifiable rewards, SCOUT improves the teacher’s performance on student prefixes. Experiments across various teacher‑student setups, model scales, and reasoning domains show that SCOUT consistently enhances the effectiveness of OPD.
On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of...
arXiv:2610.18613v1 Announce Type: cross Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as corr...
arXiv:2607. 15161v1 Announce Type: new Abstract: On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model.