Saved in:
Bibliographic Details
Main Authors: Dalal, Dwip, Mishra, Utkarsh, Ahuja, Narendra, Jojic, Nebojsa
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.15933
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912895608029184
author Dalal, Dwip
Mishra, Utkarsh
Ahuja, Narendra
Jojic, Nebojsa
author_facet Dalal, Dwip
Mishra, Utkarsh
Ahuja, Narendra
Jojic, Nebojsa
contents Leveraging multimodal large language models (MLLMs) to develop embodied agents offers significant promise for addressing complex real-world tasks. However, current evaluation benchmarks remain predominantly language-centric or heavily reliant on simulated environments, rarely probing the nuanced, knowledge-intensive reasoning essential for practical, real-world scenarios. To bridge this critical gap, we introduce the task of Sparsely Grounded Visual Navigation, explicitly designed to evaluate the sequential decision-making abilities of MLLMs in challenging, knowledge-intensive real-world environment. We operationalize this task with CityNav, a comprehensive benchmark encompassing four diverse global cities, specifically constructed to assess raw MLLM-driven agents in city navigation. Agents are required to rely solely on visual inputs and internal multimodal reasoning to sequentially navigate 50+ decision points without additional environmental annotations or specialized architectural modifications. Crucially, agents must autonomously achieve localization through interpreting city-specific cues and recognizing landmarks, perform spatial reasoning, and strategically plan and execute routes to their destinations. Through extensive evaluations, we demonstrate that current state-of-the-art MLLMs, reasoning techniques (e.g., GEPA, chain-of-thought, reflection) and competitive baseline PReP significantly underperform in this challenging setting. To address this, we propose Verbalization of Path(VoP), which explicitly grounds the agent's internal reasoning by probing city-scale cognitive maps (key landmarks and directions toward the destination) from the MLLM, substantially enhancing navigation success. Project Webpage: https://dwipddalal.github.io/AgentNav/
format Preprint
id arxiv_https___arxiv_org_abs_2512_15933
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs
Dalal, Dwip
Mishra, Utkarsh
Ahuja, Narendra
Jojic, Nebojsa
Computer Vision and Pattern Recognition
Leveraging multimodal large language models (MLLMs) to develop embodied agents offers significant promise for addressing complex real-world tasks. However, current evaluation benchmarks remain predominantly language-centric or heavily reliant on simulated environments, rarely probing the nuanced, knowledge-intensive reasoning essential for practical, real-world scenarios. To bridge this critical gap, we introduce the task of Sparsely Grounded Visual Navigation, explicitly designed to evaluate the sequential decision-making abilities of MLLMs in challenging, knowledge-intensive real-world environment. We operationalize this task with CityNav, a comprehensive benchmark encompassing four diverse global cities, specifically constructed to assess raw MLLM-driven agents in city navigation. Agents are required to rely solely on visual inputs and internal multimodal reasoning to sequentially navigate 50+ decision points without additional environmental annotations or specialized architectural modifications. Crucially, agents must autonomously achieve localization through interpreting city-specific cues and recognizing landmarks, perform spatial reasoning, and strategically plan and execute routes to their destinations. Through extensive evaluations, we demonstrate that current state-of-the-art MLLMs, reasoning techniques (e.g., GEPA, chain-of-thought, reflection) and competitive baseline PReP significantly underperform in this challenging setting. To address this, we propose Verbalization of Path(VoP), which explicitly grounds the agent's internal reasoning by probing city-scale cognitive maps (key landmarks and directions toward the destination) from the MLLM, substantially enhancing navigation success. Project Webpage: https://dwipddalal.github.io/AgentNav/
title City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.15933