CORTEXA
← Browse
arxivcs.ROcs.AI2026-07-01

DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation

Shaoheng Zhang, Zhichen Li, Jie Mei

Memory-based agents for discrete vision-language navigation (VLN) operate under partial observability and can exhibit systematic inference-time failures even with strong pretrained backbones. We focus on two recurring problems: stale historical evidence during memory readout and inefficient local backtracking during action selection. We present DART-VLN, a training-free inference-time framework that combines Test-Time Memory Decay, which reweights stale and redundant memory slots without modifying their stored content, with Anti-Loop Regularization, a lightweight next-hop penalty that discourages immediate reversals. DART-VLN introduces no learnable parameters and leaves the navigation backbone unchanged. Experiments on R2R and REVERIE show that memory decay consistently preserves or improves task performance while reducing runtime. Adding anti-loop regularization further shortens trajectories, reduces local backtracking, and achieves the best overall balance between navigation quality and efficiency among the evaluated GridMM variants. These results indicate that lightweight inference-time control can improve the reliability and efficiency of memory-based discrete VLN without retraining.

View free PDFSource page

Related papers

arxivcs.ROcs.AI2026-07-15

From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception

Jose Martínez-Fajardo, Pablo Pueyo, Fernando Caballero, Luis Merino

Natural language interaction provides an intuitive way for non-expert users to communicate with robotic platforms. However, transforming user requests into executable navigation actions remains a challenging task, requiring the integration of language understanding, environment p…

View free PDFSource page
arxivcs.ROcs.AI2026-06-29

Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models

Siyao Chen, Jiakang Yuan, Jiaxin Wang, Tao Chen

Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically require external environmental feedback, relying on predefined success signals to guide policy updates. I…

View free PDFSource page
arxivcs.ROcs.AI2026-07-09

FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation

Xueke Zhu, Qingyan Meng, Liutao Yu, Wei Zhang, Zhengyu Ma, Huihui Zhou, et al.

Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs. Compared with GPS-dependent or pre-programmed navigation, VLN supports intuitive human-machine interaction and stronger environm…

View free PDFSource page
arxivcs.ROcs.AI2026-07-09

A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation

Liuyi Wang, Kai Sheng, Zongtao He, Jinlong Li, Yongrui Qin, Haojie Dai, et al.

Navigation is a fundamental capability of autonomous systems, yet most existing approaches rely on highly structured models and strong prior assumptions, limiting their robustness in open and uncertain real-world environments. Vision-and-Language Navigation (VLN) offers a promisi…

View free PDFSource page
arxivcs.ROcs.AIcs.CV2026-07-01

What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language Models

Amirhosein Chahe, Tyler Naes, Jovin D'sa, Faizan M. Tariq, Sangjae Bae, Lifeng Zhou, et al.

Autonomous vehicles must safely navigate complex environments where planning-critical agents may be hidden from view. Current approaches often treat all occlusions with uniform conservatism, yielding needlessly defensive driving, or they infer hidden spaces without estimating the…

View free PDFSource page
arxivcs.ROcs.AI2026-06-25

E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation

Wen Ye, Peiyan Li, Tingyu Yuan, Yuan Xu, Xiangnan Wu, Chaoyang Zhao, et al.

Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major challenges remain unsolved: (1) reasoning can effectively improve the performance of the policy, but its scaling mechanism has seldom been studied; (2) historical info…

View free PDFSource page