Comment by E-Reverance

In my opinion its a great idea because you get reuse hidden states which allows you to do something akin to thinking/[online learning]. If you only evolve use input space outputs you're dealing with more decoding pressure.

Also related to what I was saying see these:

https://arxiv.org/pdf/2609.16372v1

https://arxiv.org/pdf/2609.01449v1 (this one is quite mindblowing cause they noise they the actual input space every time but it still works)

https://arxiv.org/pdf/2609.11801