← Back to the collection
Core recurrence ·
Huginn
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
A recurrent core refines hidden states between a prelude and a coda, scaling latent computation at inference time.
Inside the method
Prelude → [ Core ] × R → Coda
Simplified conceptual schematic. Consult the paper for the complete architecture.
- Recurrence family
- Core recurrence
- Depth control
- Variable recurrent depth
- KV / state strategy
- Recurrence-aware cache
Reading note
Huginn-0125 uses 2 prelude layers, 4 shared core layers and 2 coda layers. At mean recurrence 32, expected effective depth is 132. Independent parameters: about 3.5B.
Sources checked 2026-09-15. This catalog does not imply independent reproduction.
Cite this work
@misc{huginn2025,
title = {Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach},
author = {Jonas Geiping and Sean McLeish and Neel Jain and John Kirchenbauer and Siddharth Singh and Brian R. Bartoldson and Bhavya Kailkhura and Abhinav Bhatele and Tom Goldstein},
year = {2025},
eprint = {2502.05171},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2502.05171}
}