Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence
For researchers and developers of edge AI and AIoT systems, this vision addresses the scalability bottleneck of mobile agents due to limited on-device computation and fragmented intelligence.
This paper proposes a research agenda for scaling mobile agent systems by improving individual agent capability density through compact models and enabling collective intelligence via multi-agent collaboration, aiming to transform isolated agents into efficient, scalable distributed systems.
Mobile agent systems are emerging as a key paradigm for enabling intelligent applications on edge devices and in AIoT ecosystems. However, their scalability is fundamentally constrained by limited on-device computation and fragmented intelligence across devices. In this work, we propose a unified research agenda for scaling mobile agent systems along two complementary dimensions: (1) improving capability density of individual agents through compact foundation model design and compression, and (2) enabling collective intelligence via communication-rich multi-agent collaboration. Building on recent model and infrastructure advances, this vision aims to transform isolated mobile agents into a distributed intelligent system that is efficient and scalable.