What Survives When You Compress a Recursive Reasoner for the Edge?

Excerpt

arXiv:2606.26488v2 Announce Type: replace Abstract: Recursive reasoning models solve hard structured tasks with a few million parameters by iterating a latent state, but deploying them on edge hardware means compressing them -- and quantization noise compounds across recursive cycles rather than accumulating over output tokens, so single-pass intuitions fail. Here, we ask what survives. Across a full precision sweep and three tasks, aggressive compression preserves local prediction but destroys