Sara Neri, Eugenio Gaeta, Andrea Ceschini, Andrea Facchinetti, Giuseppe Fico · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26666 · open-access PDF
Wir untersuchen, ob das Hinzufügen eines dauerhaften Zwischenzustands, der wiederholte Updates eines schnelleren Zustands über denselben Operator integriert, die prädiktive Leistung im Verhältnis zur Basislinie jeder Modellfamilie bei passenden Parameterzahlen verbessert. Wir definieren diese Organisation operativ und implementieren sie innerhalb von drei Architekturen: dem Hierarchischen Reasoning-Modell (HRM), dem Tiny Recursive-Modell (TRM) und dem Universal Reasoning-Modell (URM).
Machine translation (Meta M2M100); the English original follows.
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 baseli
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26666, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange