Papers

Filtered to on-policy distillation · clear filter

Browse by term

continual learning 33reinforcement learning 21large language models 9vision-language models 8language models 6benchmarking 5autoregressive models 4diffusion transformers 4generative models 4multimodal learning 4robotics 4video generation 4benchmarks 3computer vision 3policy optimization 3self-distillation 3vision-language-action models 3world modeling 3agent-based systems 2autonomous agents 2calibration 2coding agents 2diffusion models 2foundation models 2image synthesis 2in-context learning 2knowledge graphs 2LLMs 2multimodal evaluation 2multimodal large language models 2

Matching papers

Multi-Turn On-Policy Distillation with Prefix Replay

7 upvotes · 16 JUL 2026 · Baohao Liao, Hanze Dong, Christof Monz et al.

This paper proposes a method to improve on-policy distillation by reusing pre-collected teacher data, allowing for faster training without interacting with the environment. Practitioners may care about this technique because it enables scalable and efficient distillation of complex agent models.

on-policy distillationcontinual learningreinforcement learningagent-environment interactionoffline reinforcement learning