{
  "id": 331,
  "url": "https://arxiv.org/abs/2607.01754v1",
  "title": "Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation",
  "summary": "On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution. However, such exploration inevitably leads to trajectories that deviate from expert demonstrations, resulting in a semantic mismatch between the executed visual stream and the original language instruction. In this work, we address this challenge by introducing Phi-Nav, a unified on-policy framework that leverages hindsight reasoning to ali",
  "authors": "Sung June Kim, Sangpil Kim, Honglak Lee",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-02T06:11:07.000Z",
  "fetched_at": "2026-07-14T14:14:28.435Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/331",
  "original_url": "https://arxiv.org/abs/2607.01754v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}