arXiv AI
Interactive Navigation Beyond Reachability: Benchmark and Agentic Framework
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 1
NavHarness: Adaptive Goals for Agentic Vision-Language Navigation
arXiv:2609.39915v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents...
arXiv Computer Vision
6d ago
SuperNav: An Agentic Navigation System for Any Task in Any Scene
SuperNav is a navigation system that leverages a pretrained multimodal large language model (MLLM) without fine‑tuning it for navigation. The system introduces an agent harness that delegates motion execution to navigation tools while the MLLM focuses on interpreting requests, understanding scenes, and making decisions. A visual‑point interface connects the model’s decisions to motion, allowing direct destination specification and feedback‑driven revision, enabling sustained navigation across varied tasks and environments.
arXiv AI
Sep 30
Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation
arXiv:2609.32292v2 Announce Type: replace-cross Abstract: Vision-and-language navigation increasingly relies on general-purpose semantic planners, yet translating correct high-level intent into relia...
arXiv AI
Jul 16
UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following
arXiv:2607. 13621v1 Announce Type: new Abstract: Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode.
arXiv AI
Jun 2
Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation
arXiv:2606. 00095v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions.
arXiv AI
Sep 1
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
The paper introduces NavMCP, a scaffolding framework that couples vision‑language models (VLMs) with navigation foundation models (NFMs) to enable long‑horizon physical‑world agents. NavMCP orchestrates three communication channels—intent, observation, and memory—to allow the VLM to decide what evidence to seek and the NFM to ground semantic sub‑goals into closed‑loop navigation, without retraining either model. The approach achieves state‑of‑the‑art results on several embodied question‑answering benchmarks and significantly outperforms episodic interfaces on the Unitree Go2 robot as task horizons lengthen.