Administrative Decentralization in Edge-Cloud Multi-Agent for Mobile Automation
2026-04-09 • Distributed, Parallel, and Cluster Computing
Distributed, Parallel, and Cluster Computing
AI summaryⓘ
The authors introduce AdecPilot, a new way to split decision-making between cloud and edge devices for mobile automation. Instead of relying mostly on the cloud for control, their system lets edge devices handle real-time, tactical tasks while the cloud focuses on high-level planning. This makes the system faster, more accurate, and less dependent on constant cloud communication. Their experiments show better task success, lower cloud usage, and much faster responses compared to existing methods.
edge computingcloud computingmobile automationmulti-agent systemsUI dynamicsadministrative decentralizationtactical planningHierarchical Implicit Terminationtask success ratelatency
Authors
Senyao Li, Zhigang Zuo, Haozhao Wang, Junyu Chen, Zhanbo Jin, Ruixuan LI
Abstract
Collaborative edge-cloud frameworks have emerged as the main- stream paradigm for mobile automation, mitigating the latency and privacy risks inherent to monolithic cloud agents. However, existing approaches centralize administration in the cloud while relegating the device to passive execution, inducing a cognitive lag regard- ing real-time UI dynamics. To tackle this, we introduce AdecPilot by applying the principle of administrative decentralization to the edge-cloud multi-agent framework, which redefines edge agency by decoupling high-level strategic designing from tactical grounding. AdecPilot integrates a UI-agnostic cloud designer generating ab- stract milestones with a bimodal edge team capable of autonomous tactical planning and self-correction without cloud intervention. Furthermore, AdecPilot employs a Hierarchical Implicit Termi- nation protocol to enforce deterministic stops and prevent post- completion hallucinations. Extensive experiments demonstrate pro- posed approach improves task success rate by 21.7% while reducing cloud token consumption by 37.5% against EcoAgent and decreas- ing end to end latency by 88.9% against CORE. The source code is available at https://anonymous.4open.science/r/Anonymous_code- B8AB.