EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning

• URL: http://arxiv.org/abs/2506.01551v3
• Date: Tue, 14 Oct 2025 02:26:03 GMT
• Title: EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
• Authors: Bingqian Lin, Yunshuang Nie, Khun Loun Zai, Ziming Wei, Mingfei Han, Rongtao Xu, Minzhe Niu, Jianhua Han, Hanwang Zhang, Liang Lin, Bokui Chen, Cewu Lu, Xiaodan Liang,
• Abstract summary: We propose EvolveNav, a novel embodied reasoning paradigm that realizes adaptable and generalizable navigational reasoning.<n>EvolveNav involves a two-stage training process: (1) Formalized CoT Supervised Fine-Tuning, where we train the model with curated formalized CoT labels to first activate the model's navigational reasoning capabilities, and simultaneously increase the reasoning speed; (2) Self-Reflective Post-Training, where the model is iteratively trained with its own reasoning outputs as self-enriched CoT labels to enhance the supervision diversity.
• Score: 145.32076310071434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies have revealed the potential of training open-source Large Language Models (LLMs) to unleash LLMs' reasoning ability for enhancing vision-language navigation (VLN) performance, and simultaneously mitigate the domain gap between LLMs' training corpus and the VLN task. However, these approaches predominantly adopt straightforward input-output mapping paradigms, causing the mapping learning difficult and the navigational decisions unexplainable. Chain-of-Thought (CoT) training is a promising way to improve both navigational decision accuracy and interpretability, while the complexity of the navigation task makes the perfect CoT labels unavailable and may lead to overfitting through pure CoT supervised fine-tuning. To address these issues, we propose EvolveNav, a novel sElf-improving embodied reasoning paradigm that realizes adaptable and generalizable navigational reasoning for boosting LLM-based vision-language Navigation. Specifically, EvolveNav involves a two-stage training process: (1) Formalized CoT Supervised Fine-Tuning, where we train the model with curated formalized CoT labels to first activate the model's navigational reasoning capabilities, and simultaneously increase the reasoning speed; (2) Self-Reflective Post-Training, where the model is iteratively trained with its own reasoning outputs as self-enriched CoT labels to enhance the supervision diversity. A self-reflective auxiliary task is also designed to encourage the model to learn correct reasoning patterns by contrasting with wrong ones. Experimental results under both task-specific and cross-task training paradigms demonstrate the consistent superiority of EvolveNav over previous LLM-based VLN approaches on various popular benchmarks, including R2R, REVERIE, CVDN, and SOON. Code is available at https://github.com/expectorlin/EvolveNav.

Related papers

• Learning to Retrieve Navigable Candidates for Efficient Vision-and-Language Navigation [15.242490558864626]
  Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions and navigate through previously unseen environments.<n>We propose a retrieval-augmented framework to improve VLN without modifying or fine-tuning the underlying language model.
  arXiv  Detail & Related papers  (2026-02-17T17:00:11Z)
• VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory [43.2995099083993]
  VLA models have shown promising potential in embodied navigation by unifying perception and planning.<n>Most existing VLA models rely on reactive mappings directly from observations to actions.<n>We propose VLingNav, a VLA model for embodied navigation grounded in linguistic-driven cognition.
  arXiv  Detail & Related papers  (2026-01-13T15:43:43Z)
• 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)
• NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models [30.685419129265252]
  We bridge the divide between VLN-specialized models and LLM-based navigation paradigms. We exploit a way to incorporate LLMs and navigation policy networks for effective action predictions and navigational reasoning.
  arXiv  Detail & Related papers  (2024-07-17T07:44:26Z)
• TINA: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation [11.591176410027224]
  This paper presents a Vision-Language Navigation (VLN) agent based on Large Language Models (LLMs) We propose the Thinking, Interacting, and Action framework to compensate for the shortcomings of LLMs in environmental perception. Our approach also outperformed some supervised learning-based methods, highlighting its efficacy in zero-shot navigation.
  arXiv  Detail & Related papers  (2024-03-13T05:22:39Z)
• 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)
• NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models [17.495162643127003]
  We introduce the NavGPT to reveal the reasoning capability of GPT models in complex embodied scenes. NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status. We show that NavGPT is capable of generating high-quality navigational instructions from observations and actions along a path.
  arXiv  Detail & Related papers  (2023-05-26T14:41:06Z)
• BEVBert: Multimodal Map Pre-training for Language-guided Navigation [75.23388288113817]
  We propose a new map-based pre-training paradigm that is spatial-aware for use in vision-and-language navigation (VLN) We build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map. Based on the hybrid map, we devise a pre-training framework to learn a multimodal map representation, which enhances spatial-aware cross-modal reasoning thereby facilitating the language-guided navigation goal.
  arXiv  Detail & Related papers  (2022-12-08T16:27:54Z)
• Cross-modal Map Learning for Vision and Language Navigation [82.04247028482244]
  We consider the problem of Vision-and-Language Navigation (VLN) In contrast to other works, our key insight is that the association between language and vision is stronger when it occurs in explicit spatial representations. We propose a cross-modal map learning model for vision-and-language navigation that first learns to predict the top-down semantics on an egocentric map for both observed and unobserved regions.
  arXiv  Detail & Related papers  (2022-03-10T03:30:12Z)
• Contrastive Instruction-Trajectory Learning for Vision-Language Navigation [66.16980504844233]
  A vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works fail to discriminate the similarities and discrepancies across instruction-trajectory pairs and ignore the temporal continuity of sub-instructions. We propose a Contrastive Instruction-Trajectory Learning framework that explores invariance across similar data samples and variance across different ones to learn distinctive representations for robust navigation.
  arXiv  Detail & Related papers  (2021-12-08T06:32:52Z)
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning [66.9937776799536]
  The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments. We propose a cross-modal grounding module to equip the agent with a better ability to track the correspondence between the textual and visual modalities.
  arXiv  Detail & Related papers  (2020-11-22T09:13:46Z)

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.