Less is More: Recursive Reasoning with Tiny Networks

2025-10-06 · Alexia Jolicoeur-Martineau arxiv

Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and ARC-AGI while trained with small models (27M parameters) on small data (around 1000 examples). HRM holds great promise for solving hard problems with small networks, but it is not yet well understood and may be suboptimal. We propose Tiny Recursive Model (TRM), a much simpler recursive reasoning approach that achieves significantly higher generalization than HRM, while using a single tiny network with only 2 layers. With only 7M parameters, TRM obtains 45% test-accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, higher than most LLMs (e.g., Deepseek R1, o3-mini, Gemini 2.5 Pro) with less than 0.01% of the parameters.

📄 PDF Abstract BibTeX arXiv:2510.04871

Code (0)

등록된 구현이 없습니다.

Tab-TRM: Tiny Recursive Model for Insurance Pricing on Tabular Data

2026-01-12 · Kishan Padayachy, Ronald Richman, Mario V. Wüthrich arxiv

We introduce Tab-TRM (Tabular-Tiny Recursive Model), a network architecture that adapts the recursive latent reasoning paradigm of Tiny Recursive Models (TRMs) to insurance modeling. Drawing inspiration from both the Hie…

Tiny Recursive Reasoning with Mamba-2 Attention Hybrid

2026-02-12 · Wenlong Wang, Fergal Reid arxiv

Recent work on recursive reasoning models like TRM demonstrates that tiny networks (7M parameters) can achieve strong performance on abstract reasoning tasks through latent recursion -- iterative refinement in hidden rep…

Energy-guided Recursive Model

2026-07-11 · Yifei Zhao, Ying Tang arxiv

Recursive reasoning models address structured problems by repeatedly updating latent states of small neural networks. However, their test-time scaling lacks a principled inference mechanism: increasing depth or stochasti…

Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement

2026-03-19 · Ange-Clément Akazan, Abdoulaye Koroko, Verlon Roel Mbingui, Choukouriyah Arinloye 외 arxiv

The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are pa…

Image Classification

Recursive Inference Machines for Neural Reasoning

2026-03-05 · Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus, Sriraam Natarajan 외 arxiv

Neural reasoners such as Tiny Recursive Models (TRMs) solve complex problems by combining neural backbones with specialized inference schemes. Such inference schemes have been a central component of stochastic reasoning …