Chain-of-Thought and Compressed Looped Transformers: A Memory-Budget Separation

ArXi:2605.30757v1 Announce Type: new Chain-of-thought prompting and looped Transformers both give a fixed model test-time computation, but they differ in what they remember. Chain-of-thought s intermediate state in generated tokens that remain in the context, whereas a looped Transformer carries state through recurrent hidden activations. We argue that this persistent mutable memory is a central resource for test-time reasoning. We compare three memory regimes, the compressed latent loop, the full sequence-state loop, and the chain-of-thought scratchpad.