This paper develops a method to improve reasoning models by reducing the discrepancy between a stronger teacher and an on-policy student, which helps to prevent the student from learning the teacher's own flaws. Practitioners might care because it can lead to more accurate models that better represent the capability gap between teachers and students.
Firehose
Filtered to tagged “on-policy distillation” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 82continual learning 29AI 26agentic coding 17reinforcement learning 16open-weight models 11AI agents 10AI safety 9AI ethics 8cybersecurity 8machine learning 7open-source 7language models 6natural language processing 6Reinforcement learning 6artificial general intelligence 5deep learning 5Diffusion models 5Agentic AI 4computer vision 4conversational AI 4ethics 4existential risk 4large language models 4LLMs 4Recursive self-improvement 4robotics 4security 4vision-language models 4ai 3
This paper proposes a new method for self-retiring on-policy distillation in agentic reinforcement learning, which allows agents to learn more effectively by switching between teacher-student training and reinforcement learning alone. Practitioners might care about this approach because it can improve the performance of agents in complex tasks.
This paper investigates why some AI models can generate excessively long responses and proposes a solution to mitigate this issue by aligning the models' termination tokens. Practitioners might care about this problem because it can lead to wasted generation budgets and inefficient AI applications.