AI RESEARCH

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

arXiv CS.CV

ArXi:2602.02220v2 Announce Type: replace Language-conditioned goal navigation (LGN) requires agents to locate user-specified targets without step-by-step guidance. However, existing benchmarks largely focus on category-level goals or rely on instance descriptions generated by vision-language models (VLMs), which often contain ambiguities and semantic errors, limiting systematic and reliable evaluation. We