Tinker
@tinkerapi
I tink, therefore I am.
Post-training API by @thinkymachines
加入 January 2026
1 正在關注 13.4K 粉絲
Exciting work from @wzenus, supported by Tinker grants!
In Agent RL, models suffer from Template Collapse.
They generate vast, diverse outputs (High Entropy) that lose all meaningful connection to the input prompt (Low Mutual Information).
In other words, agent learn different ways to say nothing.
🚀 Introducing RAGEN-v2 -- Here's how we define and fix such silent failure modes in Agent RL. 🧵
顯示更多
