Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Tianyi, Zhang, Yue, Wang, Zehao, Kordjamshidi, Parisa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909038635122688
author Ma, Tianyi
Zhang, Yue
Wang, Zehao
Kordjamshidi, Parisa
author_facet Ma, Tianyi
Zhang, Yue
Wang, Zehao
Kordjamshidi, Parisa
contents Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments. While recent progress has been driven by large-scale pre-training and data augmentation, current methods still struggle to generalize to unseen scenarios, particularly when complex spatial and temporal reasoning is required. In this work, we propose SkillNav, a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents. Our method decomposes navigation into a set of interpretable atomic skills (e.g., Vertical Movement, Area and Region Identification, Stop and Pause), each handled by a specialized agent. To support targeted skill training without manual data annotation, we construct a synthetic dataset pipeline that generates diverse, linguistically natural, skill-specific instruction-trajectory pairs. We then introduce a novel training-free Vision-Language Model (VLM)-based router, which dynamically selects the most suitable agent at each time step by aligning sub-goals with visual observations and historical actions. SkillNav obtains competitive results on commonly used benchmarks and establishes state-of-the-art generalization to the GSA-R2R, a benchmark with novel instruction styles and unseen environments.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07642
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
Ma, Tianyi
Zhang, Yue
Wang, Zehao
Kordjamshidi, Parisa
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments. While recent progress has been driven by large-scale pre-training and data augmentation, current methods still struggle to generalize to unseen scenarios, particularly when complex spatial and temporal reasoning is required. In this work, we propose SkillNav, a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents. Our method decomposes navigation into a set of interpretable atomic skills (e.g., Vertical Movement, Area and Region Identification, Stop and Pause), each handled by a specialized agent. To support targeted skill training without manual data annotation, we construct a synthetic dataset pipeline that generates diverse, linguistically natural, skill-specific instruction-trajectory pairs. We then introduce a novel training-free Vision-Language Model (VLM)-based router, which dynamically selects the most suitable agent at each time step by aligning sub-goals with visual observations and historical actions. SkillNav obtains competitive results on commonly used benchmarks and establishes state-of-the-art generalization to the GSA-R2R, a benchmark with novel instruction styles and unseen environments.
title Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.07642