{"ID":6138262,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T13:31:09.21043372Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07403","arxiv_id":"2607.07403","title":"Multi-Agent Robotic Control with Onboard Vision-Language Models","abstract":"Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control. Yet, they face significant challenges regarding explainability, generalization, and compute requirements. This paper presents a Multi-Agent System (MAS) architecture that addresses these limitations by deploying specialized agents on onboard hardware - eliminating dependence on external compute. The system controls a multi-purpose autonomous mobile manipulator in a simulated industrial warehouse, fulfilling five task categories: safety inspection, warehouse maintenance, warehouse search, package quality verification, and responding to human requests. Compact VLMs (3-20B parameters) are used throughout, with fine-tuning applied to improve package inspection accuracy. A novel \"Megamind\" orchestration agent mitigates context retention issues inherent to long-horizon planning with smaller models. The system was validated in a hardware-in-the-loop simulation using an AMD Ryzen(TM) AI mini PC. Results demonstrate that a fully onboard MAS architecture is a viable, cost-efficient alternative to cloud-dependent deployments, with strong potential for real-world transfer. The simulation environment has been released as open source under the Apache 2.0 licence.","short_abstract":"Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control. Yet, they face significant challenges regarding explainability, generalization, and compute requirements. This paper presents a Multi-Agent System (MAS) architecture that addresses these limitations by deploying...","url_abs":"https://arxiv.org/abs/2607.07403","url_pdf":"https://arxiv.org/pdf/2607.07403v1","authors":"[\"Kajetan Rachwał\",\"Maciej Majek\",\"Bartłomiej Boczek\",\"Jakub Matejczyk\",\"Dominik Matejkowski\",\"Adam Dąbrowski\",\"Tim Seyde\",\"Alexander Amini\",\"Maria Ganzha\"]","published":"2026-07-08T13:37:31Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}