{"slug": "closer-vln-closed-loop-self-verified-retrieval-augmented-reasoning-for-aerial", "title": "CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation", "summary": "Researchers propose CLOSER-VLN, a closed-loop self-verified retrieval-augmented reasoning method for aerial vision-language navigation that verifies and corrects actions before execution. The method achieves 32.01% success rate and 21.28% SPL on the CityNav benchmark, addressing error accumulation in open-loop approaches.", "body_md": "arXiv:2606.28397v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/closer-vln-closed-loop-self-verified-retrieval-augmented-reasoning-for-aerial", "canonical_source": "https://arxiv.org/abs/2606.28397", "published_at": "2026-06-30 04:00:00+00:00", "updated_at": "2026-06-30 04:25:02.367536+00:00", "lang": "en", "topics": ["computer-vision", "natural-language-processing", "large-language-models", "robotics", "ai-agents"], "entities": ["CLOSER-VLN", "CityNav", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/closer-vln-closed-loop-self-verified-retrieval-augmented-reasoning-for-aerial", "markdown": "https://wpnews.pro/news/closer-vln-closed-loop-self-verified-retrieval-augmented-reasoning-for-aerial.md", "text": "https://wpnews.pro/news/closer-vln-closed-loop-self-verified-retrieval-augmented-reasoning-for-aerial.txt", "jsonld": "https://wpnews.pro/news/closer-vln-closed-loop-self-verified-retrieval-augmented-reasoning-for-aerial.jsonld"}}