Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
•
67
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Support Tokens, Stability Margins, and a New Foundation for Robust LLMs
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Articles
LinkedIn 's datasets
None public yet