ARLoop: Fully-Open Pre-trained Looped Transformers with Attention Residuals
Combines shared transformer layers with attention over recent residual states across recurrent depths. Evaluates the design in controlled pretraining and releases models trained on open language, math and code data.
First public: · Added to this list: November 9, 2026
Explore this approach
Recurrent reasoning — Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.