Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task navigation guided by complex, long-horizon language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such multi-task instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a navigation model built on a hierarchical planning framework. Our SeqWalker features: i) A High-Level Planner that dynamically selects global instructions into contextually relevant sub-instructions based on the agent's current visual observations, thus reducing cognitive load; ii) A Low-Level Planner incorporating an Exploration-Verification strategy that leverages the inherent logical structure of instructions for trajectory error correction. To evaluate SH-VLN performance, we also extend the IVLN dataset and establish a new benchmark. Extensive experiments are performed to demonstrate the superiority of the proposed SeqWalker.
@article{arxiv.2601.04699,
title = {SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning},
author = {Zebin Han and Xudong Wang and Baichen Liu and Qi Lyu and Zhenduo Shang and Jiahua Dong and Lianqing Liu and Zhi Han},
journal= {arXiv preprint arXiv:2601.04699},
year = {2026}
}