NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime

arXiv:2610.10787 · cs.RO, cs.AI, cs.CL, cs.CV, cs.LG · Submitted 2026-10-07 · Read on arXiv

cs.RO, cs.AI, cs.CL, cs.CV, cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/deepseek-ai/deepseek-harness

Project page: https://metacognitionai.github.io/NavGPT3/ABSTRACT

Terminology

• Grounding — 18× in this paper · explained in 3 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Foundation Model — 8× in this paper · explained in 3 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Allocator — 5× in this paper · explained in 1 episode
• In Vision-and-Language Navigation — 4× in this paper
• Abstraction — 3× in this paper · explained in 1 episode
• Fidelity — 3× in this paper · explained in 2 episodes
• Visual Grounding — 3× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Action Bias — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Active Exploration — 1× in this paper · explained in 2 episodes
• Affordance — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Full-duplex interaction — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Metacognition — 1× in this paper · explained in 5 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• State Management — 1× in this paper · explained in 3 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
• LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
• ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
• MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation
• AstraNav-World: World Model for Foresight Control and Consistency
• Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs
• Moshi: a speech-text foundation model for real-time dialogue
• VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
• PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot Manipulation
• What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents
• DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction
• From Routes to Steps: Separating Semantic Progress from Local Execution in Vision-and-Language Navigation
• Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
• RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
• HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
• Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions
• Robostral Navigate
• LangNav: Language as a Perceptual Representation for Navigation
• Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving