Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence

TL;DR

This paper proposes a dual approach to scale mobile agent systems by enhancing individual agent capabilities with compact models and fostering collective intelligence through multi-agent collaboration.

Contribution

It introduces a unified research agenda combining model compression and multi-agent communication to enable scalable, distributed mobile agent systems.

Findings

Advocates for compact foundation models to improve agent capability density.

Highlights the importance of communication-rich multi-agent collaboration.

Aims to transform isolated agents into efficient, scalable distributed systems.

Abstract

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.