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

Korean

반복적 추론 모델은 학습된 운영자를 반복적으로 적용함으로써 지속적인 내부 상태를 정밀화합니다. 우리는 동일한 운영자를 통해 더 빠른 상태의 반복 업데이트를 통합하는 지속적인 중간 상태를 추가하면 각 모델 가족의 기준선에 비해 예측 성능이 향상되는지 여부를 조사합니다. 우리는이 조직을 운영적으로 정의하고 세 개의 아키텍처 내에서 구현합니다 : 계층적 추론 모델 (HRM), 소규모 추론 모델 (TRM) 및 유니버설 추론 모델 (URM). ARC-AGI-1의 공식 코드베이스를 사용하여 각 기초선을 파라미터와 일치하는 둥근 변형과 비교합니다. 우리는 훈련 중에 사용할 수 있었던 데모션을 가진 작업에서 개최된 쿼리를 평가합니다. 실험

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