# Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale

arXiv: https://arxiv.org/abs/2509.24910 · HTML: https://mlsanity.com/paper/2509.24910/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2025.

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

- [ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI](https://mlsanity.com/paper/2607.04426/) (2026)
- [Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction](https://mlsanity.com/paper/2606.05769/) (2026)
- [Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping](https://mlsanity.com/paper/2610.15782/) (2026)

## Abstract (arXiv)

Goal-oriented vision-language navigation requires robust exploration capabilities for agents to navigate to specified goals in unknown environments without step-by-step instructions. Existing methods tend to exclusively utilize shortest-path trajectories, lacking effective exploration priors for training navigation agents. To address the above challenges, we present SID, a goal-oriented vision-and-language navigation learning approach with Self-Improving Demonstrations. Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories. The novel rollouts provide demonstrations with stronger exploration strategies to train a better agent, which in turn produces higher-quality agent demonstrations for the next round of training. We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations are highly transferable, elevating the performance ceiling across a variety of vision-and-language navigation tasks. Extensive experiments demonstrate that SID significantly boosts the exploration capabilities and generalization of navigation agents. The resulting agent achieves new state-of-the-art performance on goal-oriented vision-and-language navigation benchmarks, including REVERIE, SOON as well as strong transferability to object-goal navigation and VLN-CE. It notably achieves a 50.9% success rate on the unseen validation splits of SOON, surpassing prior leading approaches by a margin of 13.9%.