# Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping

arXiv: https://arxiv.org/abs/2610.15782 · HTML: https://mlsanity.com/paper/2610.15782/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 63 of its 69 references that are in the map.
- First posted on arXiv 11 Oct 2026.

## Builds on (most cited first, 30 of 63)

- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [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)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [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)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [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)
- [Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://mlsanity.com/paper/1904.04195/) (2019)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training](https://mlsanity.com/paper/2002.10638/) (2020)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2202.11742/) (2022)
- [ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2304.03047/) (2023)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment](https://mlsanity.com/paper/2406.04882/) (2024)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [Dual Learning for Machine Translation](https://mlsanity.com/paper/1611.00179/) (2016)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023)

## Abstract (arXiv)

Vision-language navigation requires agents to follow natural-language instructions to reach target locations, making high-quality language supervision essential. Since human annotation is costly, prior work has explored scalable data synthesis methods. However, existing methods typically either use separate models for navigation and instruction generation or couple the two tasks through task-specific components; most also annotate the full trajectory corpus with a fixed model before updating, which can cause generated supervision to lag behind the evolving policy. Therefore, we introduce RSI-Nav, a data-centric recursive self-improvement framework for navigation via policy-synchronized language-action dual bootstrapping, which unifies vision-language-to-action instruction following and vision-action-to-language instruction generation within a shared model. Specifically, after supervised fine-tuning establishes fundamental capabilities, RSI-Nav progressively processes unlabeled trajectories in small shards. The current model generates instructions for these trajectories, executes them to evaluate goal completion and path efficiency, retains qualified samples, and immediately updates itself before processing the next shard. This shard-wise update keeps newly generated supervision aligned with the evolving policy. We also incorporate spatial understanding data, since stronger spatial reasoning benefits navigation. Extensive experiments show that RSI-Nav reaches 68.6% SR on R2R-CE and 72.4% SR on RxR-CE, while providing stronger instruction-generation utility and modestly improved spatial understanding after recursive evolution.