# FireNav: Decision-Oriented Reconstruction Evidence Routing for Vision-Language Navigation in Indoor Fire Environments

arXiv: https://arxiv.org/abs/2610.15595 · HTML: https://mlsanity.com/paper/2610.15595/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 33 references that are in the map.
- First posted on arXiv 11 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation](https://mlsanity.com/paper/2512.08186/) (2025)
- [UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior](https://mlsanity.com/paper/2501.13134/) (2025)
- [Degradation-Aware Feature Perturbation for All-in-One Image Restoration](https://mlsanity.com/paper/2505.12630/) (2025)
- [OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation](https://mlsanity.com/paper/2509.25687/) (2025)
- [Universal Image Restoration Pre-training via Degradation Classification](https://mlsanity.com/paper/2501.15510/) (2025)
- [Adaptive Action Chunking at Inference-time for Vision-Language-Action Models](https://mlsanity.com/paper/2604.04161/) (2026)
- [Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities](https://mlsanity.com/paper/2507.13019/) (2025)
- [Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing](https://mlsanity.com/paper/2503.13147/) (2025)
- [Towards Physically Executable 3D Gaussian for Embodied Navigation](https://mlsanity.com/paper/2510.21307/) (2025)
- [UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity](https://mlsanity.com/paper/2412.20157/) (2024)
- [From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning](https://mlsanity.com/paper/2507.22028/) (2025)
- [Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation](https://mlsanity.com/paper/2511.17097/) (2025)
- [Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration](https://mlsanity.com/paper/2504.09377/) (2025)
- [CompassNav: Steering From Path Imitation To Decision Understanding In Navigation](https://mlsanity.com/paper/2510.10154/) (2025)
- [AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation](https://mlsanity.com/paper/2605.22816/) (2026)
- [Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video](https://mlsanity.com/paper/2412.11395/) (2024)
- [MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization](https://mlsanity.com/paper/2511.19878/) (2025)
- [Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration](https://mlsanity.com/paper/2603.01725/) (2026)
- [VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing](https://mlsanity.com/paper/2510.05213/) (2025)
- [Image Quality Assessment for Embodied AI](https://mlsanity.com/paper/2505.16815/) (2025)
- [SmokeBench: A Real-World Dataset for Surveillance Image Desmoking in Early-Stage Fire Scenes](https://mlsanity.com/paper/2509.12701/) (2025)
- [TaskTok: Delving into Task Tokens for Task-driven Image Restoration](https://mlsanity.com/paper/2606.26615/) (2026)
- [All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation](https://mlsanity.com/paper/2603.14276/) (2026)
- [x2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space](https://mlsanity.com/paper/2603.16671/) (2026)

## Abstract (arXiv)

In real-world indoor fire environments, visual degradation severely impairs instruction grounding, waypoint prediction, and long-horizon exploration in vision-language navigation (VLN). Although image restoration offers a natural means to mitigate such visual degradation, existing methods primarily optimize reconstruction fidelity, which does not necessarily translate into better navigation decisions and may even corrupt task-critical cues when applied indiscriminately. In this paper, we present FireNav, a decision-oriented reconstruction evidence routing framework that aligns visual restoration with navigation utility in VLN. To advance this task, we first contribute FireVLN-Bench, a paired indoor fire navigation benchmark with clean references preserving task semantics, safety supervision, and matched settings for continuous navigation and robot execution with simulated dynamics. Our FireNav retains native visual tokens and treats latent reconstruction features as auxiliary evidence, where a lightweight router leverages visual features, task context, and prior execution states to determine whether such evidence should be admitted and how strongly it should contribute to the visual tokens. To learn when reconstruction is beneficial, we further introduce decision utility calibration, which compares action prediction losses with and without candidate evidence under the same state, thereby supervising evidence selection according to its contribution to waypoint, heading, and arrival prediction. Experiments demonstrate that FireNav consistently outperforms state-of-the-art baselines in both navigation success and path efficiency across evaluation settings.