Recursive Inference Machines for Neural Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Komisarczyk, Mieszko, Mathur, Saurabh, Kraus, Maurice, Natarajan, Sriraam, Kersting, Kristian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910042458947584
author Komisarczyk, Mieszko
Mathur, Saurabh
Kraus, Maurice
Natarajan, Sriraam
Kersting, Kristian
author_facet Komisarczyk, Mieszko
Mathur, Saurabh
Kraus, Maurice
Natarajan, Sriraam
Kersting, Kristian
contents 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 systems, where inference rules are applied to a stochastic model to derive answers to complex queries. In this work, we bridge these two paradigms by introducing Recursive Inference Machines (RIMs), a neural reasoning framework that explicitly incorporates recursive inference mechanisms inspired by classical inference engines. We show that TRMs can be expressed as an instance of RIMs, allowing us to extend them through a reweighting component, yielding better performance on challenging reasoning benchmarks, including ARC-AGI-1, ARC-AGI-2, and Sudoku Extreme. Furthermore, we show that RIMs can be used to improve reasoning on other tasks, such as the classification of tabular data, outperforming TabPFNs.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05234
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Recursive Inference Machines for Neural Reasoning
Komisarczyk, Mieszko
Mathur, Saurabh
Kraus, Maurice
Natarajan, Sriraam
Kersting, Kristian
Machine Learning
Artificial Intelligence
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 systems, where inference rules are applied to a stochastic model to derive answers to complex queries. In this work, we bridge these two paradigms by introducing Recursive Inference Machines (RIMs), a neural reasoning framework that explicitly incorporates recursive inference mechanisms inspired by classical inference engines. We show that TRMs can be expressed as an instance of RIMs, allowing us to extend them through a reweighting component, yielding better performance on challenging reasoning benchmarks, including ARC-AGI-1, ARC-AGI-2, and Sudoku Extreme. Furthermore, we show that RIMs can be used to improve reasoning on other tasks, such as the classification of tabular data, outperforming TabPFNs.
title Recursive Inference Machines for Neural Reasoning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.05234