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

• URL: http://arxiv.org/abs/2508.07642v2
• Date: Wed, 01 Oct 2025 00:48:33 GMT
• Title: Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
• Authors: Tianyi Ma, Yue Zhang, Zehao Wang, Parisa Kordjamshidi,
• Abstract summary: Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments.<n>We propose SkillNav, a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents.
• Score: 43.5771856761934
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning [77.34267241692706]
  Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions.<n>We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions.
  arXiv  Detail & Related papers  (2025-06-20T17:59:59Z)
• General Scene Adaptation for Vision-and-Language Navigation [19.215183093931785]
  Vision-and-Language Navigation (VLN) tasks mainly evaluate agents based on one-time execution of individual instructions across multiple environments.<n>We introduce GSA-VLN, a novel task requiring agents to execute navigation instructions within a specific scene and simultaneously adapt to it for improved performance over time.<n>We propose a new dataset, GSA-R2R, which significantly expands the diversity and quantity of environments and instructions for the R2R dataset.
  arXiv  Detail & Related papers  (2025-01-29T03:57:56Z)
• SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts [54.11162991206203]
  This paper consolidates diverse navigation tasks into a unified and generic framework.<n>We propose a novel State-Adaptive Mixture of Experts (SAME) model that effectively enables an agent to infer decisions.
  arXiv  Detail & Related papers  (2024-12-07T06:12:53Z)
• Cog-GA: A Large Language Models-based Generative Agent for Vision-Language Navigation in Continuous Environments [19.818370526976974]
  Vision Language Navigation in Continuous Environments (VLN-CE) represents a frontier in embodied AI. We introduce Cog-GA, a generative agent founded on large language models (LLMs) tailored for VLN-CE tasks. Cog-GA employs a dual-pronged strategy to emulate human-like cognitive processes.
  arXiv  Detail & Related papers  (2024-09-04T08:30:03Z)
• OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation [96.46961207887722]
  OVER-NAV aims to go over and beyond the current arts of IVLN techniques. To fully exploit the interpreted navigation data, we introduce a structured representation, coded Omnigraph.
  arXiv  Detail & Related papers  (2024-03-26T02:34:48Z)
• NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning [97.88246428240872]
  Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions.<n>Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability.<n>This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision.
  arXiv  Detail & Related papers  (2024-03-12T07:27:02Z)
• LangNav: Language as a Perceptual Representation for Navigation [63.90602960822604]
  We explore the use of language as a perceptual representation for vision-and-language navigation (VLN) Our approach uses off-the-shelf vision systems for image captioning and object detection to convert an agent's egocentric panoramic view at each time step into natural language descriptions.
  arXiv  Detail & Related papers  (2023-10-11T20:52:30Z)
• Accessible Instruction-Following Agent [0.0]
  We introduce UVLN, a novel machine-translation instructional augmented framework for cross-lingual vision-language navigation. We extend the standard VLN training objectives to a multilingual setting via a cross-lingual language encoder. Experiments over Room Across Room dataset prove the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-05-08T23:57:26Z)
• Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration [83.96729205383501]
  We introduce prompt-based learning to achieve fast adaptation for language embeddings. Our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE.
  arXiv  Detail & Related papers  (2022-03-08T11:01:24Z)
• Structured Scene Memory for Vision-Language Navigation [155.63025602722712]
  We propose a crucial architecture for vision-language navigation (VLN) It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment.
  arXiv  Detail & Related papers  (2021-03-05T03:41:00Z)
• A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment [9.159670926457975]
  MoViLan is a new framework for execution of visually grounded natural language instructions. We propose a modular approach to deal with the combined navigation and object interaction problem. Specifically, we propose a novel geometry-aware mapping technique for cluttered indoor environments.
  arXiv  Detail & Related papers  (2021-01-19T23:05:43Z)
• Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training [150.35927365127176]
  We present the first pre-training and fine-tuning paradigm for vision-and-language navigation (VLN) tasks. By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions. It learns more effectively in new tasks and generalizes better in a previously unseen environment.
  arXiv  Detail & Related papers  (2020-02-25T03:08:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.