# FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation

arXiv: https://arxiv.org/abs/2601.13976 · HTML: https://mlsanity.com/paper/2601.13976/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 9 of 9)

- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2203.12667/) (2022)
- [OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation](https://mlsanity.com/paper/2509.25687/) (2025)
- [Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought](https://mlsanity.com/paper/2505.15510/) (2025)
- [OctoNav: Towards Generalist Embodied Navigation](https://mlsanity.com/paper/2506.09839/) (2025)
- [VISTA: Generative Visual Imagination for Vision-and-Language Navigation](https://mlsanity.com/paper/2505.07868/) (2025)
- [RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2505.13307/) (2025)

## Built on by (most cited first, 3 of 3)

- [ABot-N1: Toward a General Visual Language Navigation Foundation Model](https://mlsanity.com/paper/2607.10383/) (2026)
- [LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning](https://mlsanity.com/paper/2603.29165/) (2026)
- [OptiSight: Bridging Semantic Reasoning and Geometric Control for Embodied Navigation](https://mlsanity.com/paper/2608.23354/) (2026)

## Abstract (arXiv)

Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while reasoning over long action sequences. Recent works, such as NavCoT and NavGPT-2, demonstrate the potential of Chain-of-Thought (CoT) reasoning for improving interpretability and long-horizon planning. Moreover, multimodal extensions like OctoNav-R1 and CoT-VLA further validate CoT as a promising pathway toward human-like navigation reasoning. However, existing approaches face critical drawbacks: purely textual CoTs lack spatial grounding and easily overfit to sparse annotated reasoning steps, while multimodal CoTs incur severe token inflation by generating imagined visual observations, making real-time navigation impractical. In this work, we propose FantasyVLN, a unified implicit reasoning framework that preserves the benefits of CoT reasoning without explicit token overhead. Specifically, imagined visual tokens are encoded into a compact latent space using a pretrained Visual AutoRegressor (VAR) during CoT reasoning training, and the model jointly learns from textual, visual, and multimodal CoT modes under a unified multi-CoT strategy. At inference, our model performs direct instruction-to-action mapping while still enjoying reasoning-aware representations. Extensive experiments on LH-VLN show that our approach achieves reasoning-aware yet real-time navigation, improving success rates and efficiency while reducing inference latency by an order of magnitude compared to explicit CoT methods.