cs.CLOct 29, 2025

Scaling Latent Reasoning via Looped Language Models

Authors: Rui-Jie ZhuZixuan WangKai HuaTianyu ZhangZiniu LiHaoran QueBoyi WeiZixin Wen+25 more

Organizations: 1ByteDance Seed · 2UC Santa Cruz · 3Princeton University · 4Mila - Quebec AI Institute · University of Montreal · 6Peking University · 7Carnegie Mellon University · 11M-A-P · University of Pennsylvania · 9Conscium · University of Manchester

Abstract

Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training data. We present and open-source Ouro, named after the recursive Ouroboros, a family of pre-trained Looped Language Models (LoopLM) that instead build reasoning into the pre-training phase through (i) iterative computation in latent space, (ii) an entropy-regularized objective for learned depth allocation, and (iii) scaling to 7.7T tokens. Ouro 1.4B and 2.6B models enjoy superior performance that match the results of up to 12B SOTA LLMs across a wide range of benchmarks. Through controlled experiments, we show this advantage stems not from increased knowledge capacity, but from superior knowledge manipulation capabilities. We also show that LoopLM yields reasoning traces more aligned with final outputs than explicit CoT. We hope our results show the potential of LoopLM as a novel scaling direction in the reasoning era. Our model is available here: http://ouro-llm.github.io.

Explore similar work

CardsList
  1. LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

    May 10, 2026Taekhyun Park, Yongjae Lee, Dohee Kim +1Upsampling