Adaptive AI Agent Placement and Migration in Edge Intelligence Systems
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud data centers, traditionally used for agent deployment, introduces significant latency. Deploying AI agents at the edge improves efficiency and reduces latency. However, edge environments present challenges due to limited and heterogeneous resources. Maintaining QoS for mobile users necessitates agent migration, which is complicated by the complexity of AI agents coordinating LLMs, task planning, memory, and external tools. This paper presents the first systematic deployment and management solution for LLM-based AI agents in dynamic edge environments. We propose a novel adaptive framework for AI agent placement and migration in edge intelligence systems. Our approach models resource constraints and latency/cost, leveraging ant colony algorithms and LLM-based optimization for efficient decision-making. It autonomously places agents to optimize resource utilization and QoS and enables lightweight agent migration by transferring only essential state. Implemented on a distributed system using AgentScope and validated across globally distributed edge servers, our solution significantly reduces deployment latency and migration costs.
Key facts. Cited by 3 papers in the map (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 6 of its 33 references that are in the map. First posted on arXiv 5 Aug 2025.
Builds on
6 of 33 references.
Closest ancestors · 1
Same direction, newest first
Other references · 5
- 2019Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computingcited by 225
- 2019A Survey on Edge Computing Systems and Toolscited by 17
- 2019Latency Minimization for Intelligent Reflecting Surface Aided Mobile Edge Computingcited by 9
- 2022AI Augmented Edge and Fog Computing: Trends and Challengescited by 7
- 2022Multi-Agent Deep Reinforcement Learning for Cost- and Delay-Sensitive Virtual Network Function Placement and Routingcited by 3
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.
- 2025AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Productioncited by 6
- 2026Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Modelscited by 2
- 2026A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocationcited by 0
- 2026A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation24 Jul 2026
- 2026Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models12 Jan 2026
- 2025AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production18 Sep 2025
Similar, not cited
Close in wording, no citation either way
- 2026Agentic Performance at the Edge: Insights from Benchmarking
- 2025HERA: Hybrid Edge-cloud Resource Allocation for Cost-Efficient AI Agents
- 2026End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services
- 2026AgentWare: Automating the Lifecycle of Agentic Applications across the Edge-to-Cloud Continuum
- 2026CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems
- 2025Resource-Aware LLM Reasoning for Mobile Edge General Intelligence
- 2026From PyTorch to the NPU: LLM-Agent-Driven Model Conversion Across Heterogeneous Inference Runtimes
- 2026Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks