CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation
Quick Answer
The CLOSER-VLN framework introduces a closed-loop self-verified retrieval-augmented reasoning method for aerial vision-language navigation, achieving 32.01% success rate (SR) and 21.28% success path length (SPL) on the CityNav benchmark.
Quick Take
The CLOSER-VLN framework introduces a closed-loop self-verified retrieval-augmented reasoning method for aerial vision-language navigation, achieving 32.01% success rate (SR) and 21.28% success path length (SPL) on the CityNav benchmark. This approach addresses critical errors in action execution by incorporating reliability verification and targeted retrieval, enhancing navigation performance in unseen environments without task-specific training.
Key Points
- CLOSER performs action reasoning, verification, retrieval, and correction in a closed-loop.
- The framework consists of a hierarchical reasoner, action verifier, and multimodal retriever.
- CLOSER-VLN achieved 32.01% SR and 21.28% SPL on the CityNav benchmark.
- The method mitigates trajectory deviations caused by minor action errors.
- No task-specific training is required for effective navigation.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Vision-language navigation (VLN) has recently advanced with large language and multimodal models, enabling agents to follow natural-language instructions in unseen environments without training a task-specific navigation policy. However, most existing VLN methods relying on large models still adopt an open-loop decision-execution approach, where candidate actions are generated from instructions and observations but are rarely verified or corrected before execution. This causes critical issues in aerial VLN, where minor errors in intermediate actions may quickly accumulate into large trajectory deviations and lead to target loss. To address this issue, we propose Closed-loop Self-verified Retrieval-augmented Reasoning (CLOSER), a training-policy-free method that sequentially performs action reasoning, reliability verification, targeted retrieval, and action correction in a closed-loop manner before executing concrete actions. We instantiate the CLOSER in aerial VLN tasks and develop a CLOSER-VLN framework, which is composed of three components: a hierarchical reasoner for generating candidate actions based on available information, a multidimensional action verifier for assessing the reliability of actions generated by the reasoner, and a verification-triggered multimodal retriever for retrieving targeted exemplars from a memory bank only when verification fails. We conduct experimental evaluations on the CityNav benchmark, where CLOSER-VLN achieves 32.01% SR and 21.28% SPL on the test-unseen split, confirming the effectiveness of closed-loop reasoning.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.28397 [cs.CV] |
| (or arXiv:2606.28397v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.28397 arXiv-issued DOI via DataCite |
Submission history
From: Xiangyu Dong [view email]
[v1]
Wed, 24 Jun 2026 05:57:42 UTC (1,150 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.