Skip to content

VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience

Sep 2026 · arXiv.org · Vol abs/2609.34687 · 0 citations · 68 references
Computer Science

TL;DR

VCN-Bench is introduced, a VCN-Bench benchmark for probing closed-loop spatial reasoning over prior visual experience in MLLMs, and MV-DualVLN is proposed, a planning-oriented baseline that jointly leverages prior video and in-episode observations.

Abstract

Spatial reasoning is fundamental to embodied agents, yet it remains unclear whether spatial understanding can be carried forward to guide sequential interactions. Existing spatial-reasoning benchmarks typically terminate at offline predictions, while navigation benchmarks evaluate spatial reasoning as part of instruction following and exploration. We introduce VCN-Bench, a \textbf{V}ideo-\textbf{C}ontextualized \textbf{N}avigation benchmark for probing closed-loop spatial reasoning over prior visual experience in MLLMs. Given a prior video covering both the initial location and destination, the agent is tasked with reasoning out the instruction-specified target and navigating toward it with the inferred spatial context. Built on Matterport3D, VCN-Bench contains five instruction types, 100k training episodes, and 1,250 evaluation episodes. Navigation serves as the primary evaluation, while diagnostic goal identification helps distinguish destination-resolution errors from subsequent navigation failures. We further propose MV-DualVLN, a planning-oriented baseline that jointly leverages prior video and in-episode observations. Experiments reveal limited navigation performance, a substantial destination-resolution-to-navigation gap, and frequent navigation failures even after correct destination identification.

View source

Similar papers

Sep 2026

Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation

This analysis reveals a gap between benchmark-oriented spatial specialization and navigation performance, and shows how aligning spatial supervision with navigation goals, phases, and decision learning improves navigation.

Xun Huang, Shi-Jia Zhao, Rong Qu et al. · 1 citation
#artificial intelligence Preprint Aug 2026

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

LightNav-0 is presented, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads, and establishes compact VLMs as a unified and transferable backbone for generalist embodied navigation.

Shao-An Wang, Ao-Cheng Luo, Fei Huang et al. · 6 citations · ⚡1
Aug 2026

ReasonWalker: Reasoning Iterative Vision-and-Language Navigation With Implicit Instructions.

This article proposes ReasonWalker, a novel navigation model designed to enable reasoning-based navigation using implicit instructions over time, and proposes a new hierarchical learning paradigm, where the model first learns navigation actions and then acquires scene associations for implicit instruction reasoning.

Xudong Wang, Bai-Cheng Liu, Jia-Hua Dong et al. · 0 citations
Preprint Oct 2026

From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models

SpatialMind is introduced, a metric-scale VLM for spatial reasoning and future prediction that substantially outperforms both general and spatially specialized models on the authors' benchmark while achieving competitive zero-shot performance on VSI-Bench, OSI-Bench, and VLM4D.

Fei-Ran Wang, Xiao-Qi Wang, Zi-Wei Li et al. · 0 citations
Sep 2026

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

This work introduces HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness and demonstrates its applicability to both navigation tasks in real-world environments.

Yang Chen, Li-Rong Che, Zhen-Yu Huang et al. · 8 citations · ⚡2
Preprint Sep 2026

Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation

A neuro-symbolic framework that combines learned VLA control with explicit task graphs and multimodal procedural memory is investigated, which positions structured symbolic reasoning and demonstration-derived visual guidance as complementary mechanisms for reliable long-horizon VLA manipulation.

Vivek Chavan, Ya-Huan Shi, O. Heimann et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.