@inproceedings{shankar-2026-learning,
    title = "Learning Shortcut Models for Efficient Recursive Reasoning",
    author = "Shankar, Shiv",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.120/",
    pages = "1351--1360",
    ISBN = "979-8-89176-393-7",
    abstract = "Recursive models that progressively refine latent representations have demonstrated strong performance on a variety of reasoning tasks. However, these models only control whether and when to stop early, not how computation is distributed. In this work, we introduce \textit{shortcut reasoning}, a framework for distilling recursive latent reasoning into a multiscale jump model that enables flexible test-time compute. We reinterpret recursive reasoning as a latent-time dynamical process and train a student model to predict the effect of multiple reasoning steps at once. To ensure robustness, we augment shortcut transitions with a repair mechanism, where a denoising variant of the base model projects latent states back onto a valid reasoning manifold. We further introduce stepwise improvement supervision, encouraging each shortcut step to increase the likelihood of the correct answer. Experiments on ARC-AGI show that our approach achieves competitive accuracy compared to recursive baselines while requiring fewer sequential updates."
}