Michael Kirchhof(@mkirchhof_):We let an agent self-improve by exploring and internalizing ”on this sort of task, keep this sort of thing in mind“ bits of self-feedback. It learned to solve tasks where the original policy failed 128 attempts in a row and GRPO flatlined. Paper: https://t.co/HWmYb2ktMt 🧵1/8

Michael Kirchhof

@mkirchhof_

RS on uncertainty quantification for agents at @Apple

가입 June 2022

380 팔로잉 중 2K 팬

Michael Kirchhof@mkirchhof_

2026.09.30 13:42

We let an agent self-improve by exploring and internalizing ”on this sort of task, keep this sort of thing in mind“ bits of self-feedback. It learned to solve tasks where the original policy failed 128 attempts in a row and GRPO flatlined. Paper: 🧵1/8