aiqbench analysis
DuoMind advances multi-robot systems by integrating vision-language-action models for execution with vision-language models for high-level semantic coordination, addressing the gap in long-horizon distributed control. The introduction of the RoboPoly benchmark provides a critical evaluation framework for these complex, closed-loop manipulation tasks under distributed architectures. This work represents a significant step toward scalable, general-purpose robotic swarms capable of reliable collaborative behavior.
DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication
arXiv:2610.02161v1 Announce Type: cross Abstract: Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings. Extending these capabilities to multi-robot systems remains challenging because robots must coordinate long-horizon behaviors while maintaining reliable, fine-grained execution. We introduce DuoMind, a distributed hierarchical framework for multi-robot coordination through semantic communication. Each robot uses a VLA-based action model for low-level execution and a VLM-based orchestrator for high-level reasoning and inter-agent coordination. At each planning step, the orchestrator at each robot reasons over the task instruction, local observations, and messages received from other robots. It then generates low-level instructions for the action model and semantic messages for peer robots. This architecture exploits the complementary strengths of pretrained models by combining the semantic reasoning capabilities of VLMs with the precise action-generation capabilities of VLAs. To address the scarcity of benchmarks for multi-robot coordination, we further develop RoboPoly, a benchmark comprising long-horizon manipulation tasks that require coordinated, closed-loop execution under distributed control. Experiments on RoboPoly and RoboTwin demonstrate that DuoMind improves multi-robot task performance, while ablation studies confirm the contributions of hierarchical orchestration and semantic communication. More details are available on our project page.
Abstract:Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings. Extending these capabilities to multi-robot systems remains challenging because robots must coordinate long-horizon behaviors while maintaining reliable, fine-grained execution. We introduce DuoMind, a distributed hierarchical framework for multi-robot coordination through semantic communication. Each robot uses a VLA-based action model for low-level execution and a VLM-based orchestrator for high-level reasoning and inter-agent coordination. At each planning step, the orchestrator at each robot reasons over the task instruction, local observations, and messages received from other robots. It then generates low-level instructions for the action model and semantic messages for peer robots. This architecture exploits the complementary strengths of pretrained models by combining the semantic reasoning capabilities of VLMs with the precise action-generation capabilities of VLAs. To address the scarcity of benchmarks for multi-robot coordination, we further develop RoboPoly, a benchmark comprising long-horizon manipulation tasks that require coordinated, closed-loop execution under distributed control. Experiments on RoboPoly and RoboTwin demonstrate that DuoMind improves multi-robot task performance, while ablation studies confirm the contributions of hierarchical orchestration and semantic communication. More details are available on our project page.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2610.02161 [cs.RO]
(or arXiv:2610.02161v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.02161 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 291 words
Related coverage
MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics
arXiv · Jun 12, 2026
CoRelNav: Collaborative Relational Navigation for Multi-Robot Spatially Constrained Semantic Navigation
arXiv · Sep 24, 2026
Distributed Model-Based Diffusion For Scalable Multi-Robot Trajectory Optimization
arXiv · Jul 24, 2026
Multi-Robot Planning and Control from CCTV Camera Networks in a Real Warehouse
arXiv · Jun 8, 2026