Papers

Filtered to multi-teacher on-policy distillation · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

22 upvotes · 27 JUL 2026 · Tianyi Men, Zhuoran Jin, Kang Liu et al.

This paper explores how to improve long-horizon planning in AI agents, which is crucial for foundation models. Practitioners might care because better planning abilities can lead to more effective and efficient decision-making in complex environments.

multi-turn planninglong-horizon planningagentic distillationsingle-teacher on-policy distillationmulti-teacher on-policy distillationcontinual learning