{"ID":6537504,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11529","arxiv_id":"2607.11529","title":"Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory","abstract":"In this paper, we tackle the Aerial Vision-and-Dialog Navigation (AVDN) task in the training-free setting for resource-efficient high-altitude UAV navigation.Naively applying MLLMs leads to unreliable navigation due to weak directional grounding and the lack of explicit spatial memory.To address these issues, we propose PSC-AVDN, a training-free framework that tightly couples a three-stage Parsing-Search-Confirmation reasoning pipeline with a Structured Spatial Memory (SSM).The parsing stage uses an LLM to convert ambiguous dialogue instructions into stable geometric directional and destination cues.A Search Chain-of-Thought (S-CoT) then performs stepwise target exploration under high-altitude observations, and a Confirmation Chain-of-Thought (C-CoT) conducts fine-grained verification around candidate regions to resolve visual ambiguity.Meanwhile, SSM integrates three complementary sources of spatial cues, including multi-scale visual observation, spatial visual memory, and structured geometric memory to provide global spatial context and long-horizon consistency.Extensive experiments on ANDH and ANDH-Full show that PSC-AVDN establishes new state-of-the-art performance in the training-free setting, matching or surpassing several finetuned methods.Code will be publicly available at: https://github.com/QY6616/PSC-AVDN","short_abstract":"In this paper, we tackle the Aerial Vision-and-Dialog Navigation (AVDN) task in the training-free setting for resource-efficient high-altitude UAV navigation.Naively applying MLLMs leads to unreliable navigation due to weak directional grounding and the lack of explicit spatial memory.To address these issues, we propos...","url_abs":"https://arxiv.org/abs/2607.11529","url_pdf":"https://arxiv.org/pdf/2607.11529v1","authors":"[\"Yu Qi\",\"Hongyu Li\",\"Shaofei Huang\",\"Tianrui Hui\",\"Yaxiong Wang\",\"Lechao Cheng\",\"Zhun Zhong\",\"Si Liu\",\"Meng Wang\"]","published":"2026-07-13T13:14:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":614208,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-14T02:54:43.516908796Z","DeletedAt":null,"paper_id":6537504,"paper_url":"https://arxiv.org/abs/2607.11529","paper_title":"Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory","repo_url":"https://github.com/QY6616/PSC-AVDN","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}