mlsanityData to 14 Oct 2026

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

arXiv 2607.01043 ↗First posted 1 Jul 2026cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Memory-based agents for discrete vision-language navigation (VLN) operate under partial observability and may exhibit systematic inference-time failures even with strong pretrained backbones. This paper addresses 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 showed that memory decay preserved or improved task performance while reducing runtime. The addition of anti-loop regularization further shortened trajectories, reduced local backtracking, and achieved 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 23 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

20 of 23 references.

References · 20

  1. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  2. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  3. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  4. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 302
  5. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  6. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  7. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 130
  8. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 124
  9. 2019The Regretful Agent: Heuristic-Aided Navigation through Progress Estimationcited by 105
  10. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  11. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  12. 2024Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Modelscited by 79
8 more
  1. 2022Target-Driven Structured Transformer Planner for Vision-Language Navigationcited by 58
  2. 2022Iterative Vision-and-Language Navigationcited by 35
  3. 2025COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigationcited by 15
  4. 2025SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Modelscited by 9
  5. 2025Active Test-time Vision-Language Navigationcited by 7
  6. 2025NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigationcited by 6
  7. 20263D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigationcited by 4
  8. 2025TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigationcited by 3

Built on by

Not cited yet.