arXiv:2607.10383v3 Announce Type: replace 
Abstract: Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typically achieve this integration via monolithic policies that map observations directly to actions, yet they often suffer from coordinate drift and poor handling of long-tail semantics. Furthermore, these black-box mappings lack interpretability, hindering the simultaneous achievement of generality, robustness, and transparency. We present ABot-N1, a step toward a general Visual Language Navigation foundation model, that addresses these challenges by decoupling cognition from control via a slow-fast architecture guided by dual visual-language signals. More specifically, a slow vision-language reasoner performs explicit Chain-of-Thought reasoning while producing a pixel goal. This compact set of image-space anchor points serves as a universal interface for diverse tasks, including point-goal, object-goal, poi-goal, instruction-following, and person-following. Subsequently, a fast action expert leverages both the textual cues and the pixel guidance to generate continuous waypoints at the native control frequency. By bridging high-level intents and low-level control through pixel-grounded anchors paired with explicit linguistic traces, our approach ensures robust, generalizable, and interpretable navigation across simulation and real-world benchmarks. ABot-N1 establishes new state-of-the-art records, delivering massive gains specifically in urban-scale navigation: boosting POI arrival by 35.0% (to 77.3%) and achieving 95.4%/92.9% SR in complex indoor and outdoor scenes. It also maintains superior robustness across object-reaching, person-following, and instruction-following tasks. New Point-Goal/POI-Goal benchmarks are released as open source to advance the field of urban-scale navigation.

تمثل المقدمة الحديثة لـ ABot-N1 تقدمًا كبيرًا في نماذج الملاحة باللغة المرئية، حيث تهدف إلى تحسين التفكير العميق للقرارات المكانية ومعالجة مشكلات مثل انحراف الإحداثيات ونقص القابلية للتفسير في النماذج الحالية. يستخدم هذا النموذج بنية بطيئة وسريعة تفصل بين الإدراك والتحكم، مستفيدًا من إشارات بصرية ولغوية مزدوجة لتحسين الأداء.

La reciente introducción de ABot-N1 marca un avance significativo en los modelos de navegación de lenguaje visual, con el objetivo de mejorar el razonamiento profundo para decisiones espaciales y abordar problemas como la deriva de coordenadas y la falta de interpretabilidad en los modelos existentes. Este modelo emplea una arquitectura lenta-rápida que separa la cognición del control, utilizando señales visuales y lingüísticas duales para un mejor rendimiento.

L'introduction récente d'ABot-N1 représente une avancée significative dans les modèles de navigation visuelle et linguistique, visant à améliorer le raisonnement profond pour les décisions spatiales tout en abordant des problèmes tels que la dérive des coordonnées et le manque d'interprétabilité des modèles existants. Ce modèle utilise une architecture lente-rapide qui sépare la cognition du contrôle, en utilisant des signaux visuels et linguistiques doubles pour améliorer les performances.

The recent introduction of ABot-N1 marks a significant advancement in Visual Language Navigation foundation models, aiming to enhance deep reasoning for spatial decisions while addressing issues such as coordinate drift and lack of interpretability in existing models. This model employs a slow-fast architecture that separates cognition from control, utilizing dual visual-language signals for improved performance.