mlsanityData to 7 Oct 2026

Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence

arXiv 2605.08124 ↗First posted 29 Apr 2026cs.DC cs.CL cs.MAcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

11 of 15 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Beyond Message Passing: A Semantic View of Agent Communication Protocols30 Mar

Other references · 10

  1. 2024AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generationcited by 31
  2. 2025Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Modelscited by 16
  3. 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaborationcited by 10
  4. 2025Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimizationcited by 9
  5. 2026Adaptive Vision-Language Model Routing for Computer Use Agentscited by 8
  6. 20251bit-Merging: Dynamic Quantized Merging for Large Language Modelscited by 5
  7. 2024Elastic On-Device LLM Servicecited by 3
  8. 2025PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recoverycited by 3
  9. 2026Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillationcited by 2
  10. 2026The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiencycited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Scaling Behavior of Single LLM-Driven Multi-Agent Systems
  2. 2026Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
  3. 2025Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
  4. 2026The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale
  5. 2026Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
  6. 2025Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey
  7. 2025Towards a Science of Scaling Agent Systems
  8. 2024MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices