{
  "id": 312,
  "url": "https://arxiv.org/abs/2607.02222v1",
  "title": "CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation",
  "summary": "Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decomposition, while the low-level action representation remains comparatively underexplored. We propose CoFL-S, a low-level vision-language-action framework that predicts a language-conditioned flow field over the robot's local visible sector and generates continuous trajectories by rolling out the predicted field. To train this low-level representation, we c",
  "authors": "Haokun Liu, Zhaoqi Ma, Yicheng Chen, Wentao Zhang, Masaki Kitagawa, Zicen Xiong et al.",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-02T14:26:55.000Z",
  "fetched_at": "2026-07-14T14:14:28.434Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/312",
  "original_url": "https://arxiv.org/abs/2607.02222v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}