GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments

arXiv:2609.29861v1 Announce Type: new Abstract: We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception, reasoning, and decision-making capabilities. Our evaluation focues on zero-shot vision-and-language navigation in continuous environments (VLN-CE) through a minimal interface in the Codex harness, aiming to unleash GPT-6-Astra's full potential for navigation. Using monocular RGB, GPT-6-Astra decides when to observe, how to move, and when to stop, without navigation-specific fine-tuning, a trained waypoint predictor, or a pre-built scene map. Our evaluation yields four main findings. First, extbf{extit{GPT-6-Astra achieves strong zero-shot navigation performance using only monocular RGB observations}}. On the common-adopted zero-shot R2R-CE benchmark, ultra reasoning achieves a success rate of extbf{extit{79.0%}}, exceeding the strongest reported zero-shot and supervised success rates by extbf{extit{13.0}} and extbf{extit{6.9}} percentage points, respectively. Second, extbf{extit{GPT-6-Astra advances multi-stage language instructions into coherent, adaptive navigation}} by grounding spatial relations, tracking task progress, and revising its actions. Third, extbf{extit{reliable route execution and goal verification remain challenging, even with ultra reasoning}}. Plausible local landmark matches do not consistently lead to correct task completion. Fourth, extbf{extit{these capabilities motivate rethinking the role of embodied learning}}. Future VLN research should build on foundation models to advance generalizable and reliable embodied intelligence.

Source: arXiv cs.RO | 2026-09-25