# Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence

arXiv: https://arxiv.org/abs/2605.08124 · HTML: https://mlsanity.com/paper/2605.08124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 11 of 11)

- [AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation](https://mlsanity.com/paper/2412.18116/) (2024)
- [Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models](https://mlsanity.com/paper/2502.12420/) (2025)
- [Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration](https://mlsanity.com/paper/2602.03647/) (2026)
- [Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization](https://mlsanity.com/paper/2510.10618/) (2025)
- [Adaptive Vision-Language Model Routing for Computer Use Agents](https://mlsanity.com/paper/2603.12823/) (2026)
- [1bit-Merging: Dynamic Quantized Merging for Large Language Models](https://mlsanity.com/paper/2502.10743/) (2025)
- [PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery](https://mlsanity.com/paper/2502.12594/) (2025)
- [Elastic On-Device LLM Service](https://mlsanity.com/paper/2409.09071/) (2024)
- [Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation](https://mlsanity.com/paper/2602.12172/) (2026)
- [The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency](https://mlsanity.com/paper/2603.17280/) (2026)
- [Beyond Message Passing: A Semantic View of Agent Communication Protocols](https://mlsanity.com/paper/2604.02369/) (2026)

## Abstract (arXiv)

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.