Robert Nishihara @robertnishihara · 01 Sep 2026
An agentic RL training guide for Qwen 3.5 397B with SkyRL. They show very large improvements with roughly 2000 expert-labeled tasks.
5 113Views
42Likes
4Reposts
3Replies
0Quotes
20Bookmarks
Is that a lot?
0.23×vs this author's median22 635 views is typical
29Percentile for this authorof 7 recent posts
1.77×vs 10K–100K median2 896 views is typical
29.76%Reachviews ÷ followers
0.96%Engagement rateof viewers reacted