Publikation
Recursive Inference Machines for Neural Reasoning
Mieszko Komisarczyk; Saurabh Mathur; Maurice Kraus; Sriraam Natarajan; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2603.05234, Pages 1-11, arXiv, 2026.
Zusammenfassung
Neural reasoners such as Tiny Recursive Mod-
els (TRMs) solve complex problems by combin-
ing neural backbones with specialized inference
schemes. Such inference schemes have been a cen-
tral 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 intro-
ducing Recursive Inference Machines (RIMs), a
neural reasoning framework that explicitly incorpo-
rates recursive inference mechanisms inspired by
classical inference engines. We show that TRMs
can be expressed as an instance of RIMs, allow-
ing us to extend them through a reweighting com-
ponent, yielding better performance on challeng-
ing reasoning benchmarks, including ARC-AGI-1,
ARC-AGI-2, and Sudoku Extreme. Furthermore,
we show that RIMs can be used to improve rea-
soning on other tasks, such as the classification of
tabular data, outperforming TabPFNs.