LongNav-R1 Zero-Shot Performance in Long-Horizon Embodied Navigation Tasks

Abstract

Abstract: This report synthesises findings from 16 peer-reviewed papers addressing the following research question: How does the task completion accuracy of small-scale 3B multimodal policies scale relative to 7B and 13B models when faced with increasing instruction complexity in embodied navigation environments. This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1 reformulates the navigation decision process as a. 20 claims were extracted from source literature; 5 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 5.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the task completion accuracy of small-scale 3B multimodal policies scale relative to 7B and 13B models when faced with increasing instruction complexity in embodied navigation environments?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance