Model Releases
VerNav: Verifier-First Low-Latency Vision-and-Language Navigation
arXiv:2609.00920v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-language instructions. Explicit
arXiv:2609.00920v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-language instructions. Explicit reasoning can improve instruction understanding and semantic grounding, but autoregressive generation at every step accumulates large decision-stage latency over multi-step navigation. We propose VerNav, a verifier-first framework for low-latency LLM-based VLN. The verifier reduces decision-stage latency by replacing per-step autoregressive generation with batched action verification, while an entropy-based adaptive generator is invoked only for uncertain decisions to produce compact state evidence. To further improve navigation performance with the verifier, we introduce a two-stage alignment scheme: (i) VPO improves local action-preference alignment in static verifier training, and (ii) step-level reinforcement fine-tuning provides dense progress rewards over multi-step navigation rollouts during dynamic task execution. Experiments on the Room-to-Room (R2R) benchmark show that the verifier-only decision path of VerNav achieves competitive navigation performance among representative LLM-based VLN agents while reducing average decision-stage LLM latency per step by more than 10imes compared with autoregressive methods.
Related
- P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation
- Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
- Structured Observation Language for Efficient and Generalizable Vision-Language Navigation
- If, Then, Otherwise: Diagnosing Conditional Branching in Vision-Language Navigation
Source: arXiv cs.CV | 2026-09-02