Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation

TL;DR

This paper introduces DACo, a dual-agent framework for scene navigation that separates global planning from local execution, significantly improving long-horizon navigation performance in complex environments.

Contribution

DACo is a novel dual-agent architecture that disentangles global reasoning from local grounding, enhancing stability and robustness in vision-and-language navigation tasks.

Findings

Achieves up to 6.5% improvement over baselines in zero-shot settings.

Effectively generalizes across different backbone models.

Improves long-horizon navigation stability and resilience.

Abstract

Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI collaboration, requiring agents to follow natural language instructions to execute coherent action sequences in complex environments. Existing approaches either rely on multiple agents, incurring high coordination and resource costs, or adopt a single-agent paradigm, which overloads the agent with both global planning and local perception, often leading to degraded reasoning and instruction drift in long-horizon settings. To address these issues, we introduce DACo, a planning-grounding decoupled architecture that disentangles global deliberation from local grounding. Concretely, it employs a Global Commander for high-level strategic planning and a Local Operative for egocentric observing and fine-grained execution. By disentangling global reasoning from local action, DACo alleviates cognitive overload and improves long-horizon stability. The framework further integrates dynamic subgoal planning and adaptive replanning to enable structured and resilient navigation. Extensive evaluations on R2R, REVERIE, and R4R demonstrate that DACo achieves 4.9%, 6.5%, 5.4% absolute improvements over the best-performing baselines in zero-shot settings, and generalizes effectively across both closed-source (e.g., GPT-4o) and open-source (e.g., Qwen-VL Series) backbones. DACo provides a principled and extensible paradigm for robust long-horizon navigation. Project page: https://github.com/ChocoWu/DACo