# Codec Allocation

NavGPT-3 connects a language-model Planner and the 8B navigation policy NavGPT VLA through a harness with an OS-like runtime: reasoning, execution, and monitoring run as threads with their own context, tools, and permissions, and the runtime assigns motion authority by event priority so the robot can be interrupted and switched between threads; the complete system reaches 81.51 SR on R2R-CE and matches human followers on RxR-CE at 90.43 SR and 78.47 nDTW, lowering the system's minimum reaction time from 3–19 s per language-model decision to 0.5–1 s per action-policy step.

NavGPT-3 connects a language-model Planner and the 8B navigation policy NavGPT VLA through a harness with an OS-like runtime: reasoning, execution, and monitoring run as threads with their own context, tools, and permissions, and the runtime assigns motion authority by event priority so the robot can be interrupted and switched between threads; the complete system reaches 81.51 SR on R2R-CE and matches human followers on RxR-CE at 90.43 SR and 78.47 nDTW, lowering the system's minimum reaction time from 3–19 s per language-model decision to 0.5–1 s per action-policy step.