# MA-CoNav: A Master-Slave Multi-Agent Framework with Hierarchical Collaboration and Dual-Level Reflection for Long-Horizon Embodied VLN

arXiv: https://arxiv.org/abs/2603.03024 · HTML: https://mlsanity.com/paper/2603.03024/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions](https://mlsanity.com/paper/2309.11382/) (2023)
- [ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions](https://mlsanity.com/paper/2303.06594/) (2023)
- [MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation](https://mlsanity.com/paper/2401.07314/) (2024)
- [NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning](https://mlsanity.com/paper/2403.07376/) (2024)
- [Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models](https://mlsanity.com/paper/2407.07035/) (2024)
- [VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.17221/) (2025)
- [Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances](https://mlsanity.com/paper/2211.15876/) (2022)
- [LangNav: Language as a Perceptual Representation for Navigation](https://mlsanity.com/paper/2310.07889/) (2023)
- [LLM Harmony: Multi-Agent Communication for Problem Solving](https://mlsanity.com/paper/2401.01312/) (2024)
- [An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems](https://mlsanity.com/paper/2505.18397/) (2025)
- [Multi-Agent Planning Using Visual Language Models](https://mlsanity.com/paper/2408.05478/) (2024)

## Built on by (most cited first, 1 of 1)

- [LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestration](https://mlsanity.com/paper/2609.15098/) (2026)

## Abstract (arXiv)

Vision-Language Navigation (VLN) aims to empower robots with the ability to perform long-horizon navigation in unfamiliar environments based on complex linguistic instructions. Its success critically hinges on establishing an efficient ``language-understanding -- visual-perception -- embodied-execution'' closed loop. Existing methods often suffer from perceptual distortion and decision drift in complex, long-distance tasks due to the cognitive overload of a single agent. Inspired by distributed cognition theory, this paper proposes MA-CoNav, a Multi-Agent Collaborative Navigation framework. This framework adopts a ``Master-Slave'' hierarchical agent collaboration architecture, decoupling and distributing the perception, planning, execution, and memory functions required for navigation tasks to specialized agents. Specifically, the Master Agent is responsible for global orchestration, while the Subordinate Agent group collaborates through a clear division of labor: an Observation Agent generates environment descriptions, a Planning Agent performs task decomposition and dynamic verification, an Execution Agent handles simultaneous mapping and action, and a Memory Agent manages structured experiences. Furthermore, the framework introduces a ``Local-Global'' dual-stage reflection mechanism to dynamically optimize the entire navigation pipeline. Empirical experiments were conducted using a real-world indoor dataset collected by a Limo Pro robot, with no scene-specific fine-tuning performed on the models throughout the process. The results demonstrate that MA-CoNav comprehensively outperforms existing mainstream VLN methods across multiple metrics.