Papers

Filtered to on-policy learning · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

Self-Supervised Visual On-Policy Distillation

158 upvotes · 14 AUG 2026 · Yijiang Li, Yijun Liang, Yunjie Tian et al.

This paper proposes a new method called Self-Supervised Visual On-Policy Distillation (S^2VOPD) that generates learning signals from asymmetric augmented views of images, allowing for effective on-policy learning without privileged information. Practitioners might care about this paper because it presents a simple yet effective way to improve performance on various perception benchmarks.

visual augmentationon-policy learningself-supervised learningdistillationreinforcement learning

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

52 upvotes · 3 SEP 2026 · Zixun Huang, Kishan Panaganti, Haitao Mi et al.

This paper introduces FlowBalance, a method that helps a reasoning model improve itself by learning from its own experiences, while avoiding overconfidence and focusing on the best solutions. Practitioners might care about this approach because it can lead to more accurate and diverse model performance.

reinforcement learningon-policy learningself-improvementverifierstrajectory balance

DAPD: Dual-Anchored Policy Distillation

51 upvotes · 3 AUG 2026 · Jianyu Wu, Yizhou Wang, Encheng Su et al.

This paper addresses a problem in self-distillation, where a student model learns to mimic the behavior of a privileged teacher, but performs poorly at inference due to a "privilege illusion". The authors propose a new method, Dual-Anchored Policy Distillation, to resolve this issue and improve performance.

self-distillationon-policy learningpolicy distillationprivilege illusioninformation asymmetryreinforcement learning