Newest papers

Nested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URM

Sara Neri, Eugenio Gaeta, Andrea Ceschini, Andrea Facchinetti, Giuseppe Fico · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26666 · cited by 0 works (OpenAlex) · open-access PDF

French

Les modèles de raisonnement récurrents raffinent les états internes persistants en appliquant à plusieurs reprises des opérateurs appris. Nous enquêtons sur la question de savoir si l'ajout d'un état intermédiaire persistant qui intègre des mises à jour répétées d'un état plus rapide à travers le même opérateur améliore les performances prédictives par rapport à la base de base de chaque famille de modèle au nombre de paramètres correspondants. Nous définissons cette organisation de manière opérationnelle et la mettons en œuvre dans trois architectures: le Modèle de raisonnement hiérarchique (HRM), le Modèle récursif minuscule (TRM) et le Modèle de raisonnement universel (URM). En utilisant les bases de codes officielles sur ARC-AGI-1, nous

Machine translation (Meta M2M100); the English original follows.

Abstract

Recursive reasoning models refine persistent internal states by repeatedly applying learned operators. We investigate whether adding a persistent intermediate state that integrates repeated updates of a faster state through the same operator improves predictive performance relative to each model family's baseline at matched parameter counts. We define this organisation operationally and implement it within three architectures: the Hierarchical Reasoning Model (HRM), Tiny Recursive Model (TRM) and Universal Reasoning Model (URM). Using the official codebases on ARC-AGI-1, we compare each baseline with its parameter-matched nested variant. We evaluate held-out queries from tasks whose demonstrations were available during training. The experiments use a single-GPU budget far below the published training protocols. Under the tested conditions, nested variants show no consistent advantage in token accuracy, predictive loss or exact solving, which remains near zero for all configurations. The results therefore leave the hypothesis open. We specify a confirmatory comparison, with an informative baseline, multiple seeds, controls that isolate nesting and predefined criteria, to determine whether this organisation merits further development.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Nesting (process), Computer science, Recursion (computer science), Baseline (sea), Operator (biology), Zero (linguistics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange