Vision-Language Navigation requires agents to act coherently over long horizons by understanding not only local visual context but also how far they have advanced within a multi-step instruction. However, recent Vision-Language-Action models focus on direct action prediction and earlier progress methods predict numeric achievements; both overlook the monotonic co-progression property of the observation and instruction sequences. Building on this insight, Progress-Think introduces semantic progress reasoning, predicting instruction-style progress from visual observations to enable more accurate navigation. To achieve this without expensive annotations, we propose a three-stage framework. In the initial stage, Self-Aligned Progress Pretraining bootstraps a reasoning module via a novel differentiable alignment between visual history and instruction prefixes. Then, Progress-Guided Policy Pretraining injects learned progress states into the navigation context, guiding the policy toward consistent actions. Finally, Progress-Policy Co-Finetuning jointly optimizes both modules with tailored progress-aware reinforcement objectives. Experiments on R2R-CE and RxR-CE show state-of-the-art success and efficiency, demonstrating that semantic progress yields a more consistent representation of navigation advancement.
@article{arxiv.2511.17097,
title = {Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation},
author = {Shuo Wang and Yucheng Wang and Guoxin Lian and Yongcai Wang and Maiyue Chen and Kaihui Wang and Bo Zhang and Zhizhong Su and Yutian Zhou and Wanting Li and Deying Li and Zhaoxin Fan},
journal= {arXiv preprint arXiv:2511.17097},
year = {2026}
}