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

arXiv: https://arxiv.org/abs/2506.01551 · HTML: https://mlsanity.com/paper/2506.01551/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 65 of its 74 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 30 of 65)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [A Recurrent Vision-and-Language BERT for Navigation](https://mlsanity.com/paper/2011.13922/) (2020)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [History Aware Multimodal Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2110.13309/) (2021)
- [Vision-and-Dialog Navigation](https://mlsanity.com/paper/1907.04957/) (2019)

## Built on by (most cited first, 4 of 4)

- [ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation](https://mlsanity.com/paper/2603.05530/) (2026)
- [CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2606.28397/) (2026)
- [Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps](https://mlsanity.com/paper/2609.03483/) (2026)
- [MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation](https://mlsanity.com/paper/2605.18956/) (2026)

## Abstract (arXiv)

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.