Research map / Vision-language and multimodal / Robot action and navigation
AgentVLN: Towards Agentic Vision-and-Language Navigation
Zihao Xin, Wentong Li, Yixuan Jiang, Ziyuan Huang, Bin Wang, Piji Li, Jianke Zhu, Jie Qin, Sheng-Jun Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add VLM-as-Brain paradigm with cross-space representation mapping (ablation) | AgentVLN-3B · R2R-CE val | SR: 38.60 -> 59.70 | Improved |
| add context-driven fine-grained self-correction (CDFG) (ablation) | AgentVLN-3B · R2R-CE val | SR: 59.70 -> 65.60 | Improved |
| add QD-PCoT (ablation) | AgentVLN-3B · R2R-CE val | SR: 65.60 -> 67.20 | Improved |
| add QD-PCoT (ablation) | AgentVLN-3B · R2R-CE val | SPL: 63.40 -> 64.70 | Improved |
| use 8 frames of temporal context instead of none (ablation) | AgentVLN-3B · R2R-CE val | SR: 56.7 -> 67.2 | Improved |
| extend history window beyond 8 frames (ablation) | AgentVLN-3B · R2R-CE val | SR / SPL | Hurt |
| AgentVLN-3B vs EfficientVLN-4B (which uses monocular depth estimation module) | AgentVLN-3B · R2R-CE val | SR: 64.2 -> 67.2 | Improved |
| AgentVLN-3B vs EfficientVLN-4B | AgentVLN-3B · R2R-CE val | OS: 73.7 -> 73.5 | Hurt |
Closest papers by meaning
- AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation (CVPR 2026 · similarity 0.92)
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (CVPR 2020 · similarity 0.92)
- Iterative Vision-and-Language Navigation (CVPR 2023 · similarity 0.91)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.91)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.91)
- SenseSearch: Empowering Vision-Language Models with High-Resolution Agentic Search-Reasoning via Reinforcement Learning (CVPR 2026 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
