SOURCE-LINKED INTELLIGENCE

Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Long-horizon physical-world agents must reason over distant goals while grounding decisions in reliable closed-loop behavior. Today's foundation models split these capabilities: vision-language models (VLMs) infer missing information and adapt high-level plans but remain brittle and inefficient at repeated navigation grounding, while navigation foundation models (NFMs) robustly execute semantic goals but operate as bounded episodes without persistent task-level reasoning. We introduce NavMCP, an agentic scaffolding framework that couples a VLM reasoning agent with an NFM executor for long-hori

Read original source ↗ Open in workspace

recordType

paper

region

Global