AgentVNE: LLM-Augmented Graph Reinforcement Learning for Affinity-Aware Multi-Agent Placement in Edge Agentic AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Runze, Zheng, Yuqing, Cheng, Zhengyi, Luo, Long, Luo, Haoxiang, Sun, Gang, Yu, Hongfang, Niyato, Dusit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915708429926400
author Zheng, Runze
Zheng, Yuqing
Cheng, Zhengyi
Luo, Long
Luo, Haoxiang
Sun, Gang
Yu, Hongfang
Niyato, Dusit
author_facet Zheng, Runze
Zheng, Yuqing
Cheng, Zhengyi
Luo, Long
Luo, Haoxiang
Sun, Gang
Yu, Hongfang
Niyato, Dusit
contents The Internet of Agents is propelling edge computing toward agentic AI and edge general intelligence (EGI). However, deploying multi-agent service (MAS) on resource-constrained edge infrastructure presents severe challenges. MAS service workflows are driven by complex cross-node interactions, dynamic memory accumulation, and collaborative tool usage. Exhibiting chain-like topological dependencies and strict affinity constraints, these workflows demand real-time responsiveness that exceeds the capabilities of traditional VNE algorithms designed for static resources. To address this, we propose AgentVNE, a cloud-edge collaborative framework utilizing a dual-layer architecture. First, AgentVNE employs a large language model (LLM) to identify implicit semantic constraints and generate affinity-based resource augmentation to resolve physical dependency issues. Second, it constructs a resource similarity-aware neural network, utilizing a pre-training and PPO fine-tuning strategy to precisely capture topological similarities between dynamic workflows and heterogeneous networks. By coupling semantic perception with topological reasoning, this mechanism effectively bridges the gap between dynamic service requirements and physical infrastructure. Simulation results demonstrate that AgentVNE reduces workflow communication latency to less than 40% of baselines and improves the service acceptance rate by approximately 5%-10% under high-load scenarios. Ultimately, this work provides a foundational solution for the semantic-aware deployment of agentic AI.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02021
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgentVNE: LLM-Augmented Graph Reinforcement Learning for Affinity-Aware Multi-Agent Placement in Edge Agentic AI
Zheng, Runze
Zheng, Yuqing
Cheng, Zhengyi
Luo, Long
Luo, Haoxiang
Sun, Gang
Yu, Hongfang
Niyato, Dusit
Networking and Internet Architecture
The Internet of Agents is propelling edge computing toward agentic AI and edge general intelligence (EGI). However, deploying multi-agent service (MAS) on resource-constrained edge infrastructure presents severe challenges. MAS service workflows are driven by complex cross-node interactions, dynamic memory accumulation, and collaborative tool usage. Exhibiting chain-like topological dependencies and strict affinity constraints, these workflows demand real-time responsiveness that exceeds the capabilities of traditional VNE algorithms designed for static resources. To address this, we propose AgentVNE, a cloud-edge collaborative framework utilizing a dual-layer architecture. First, AgentVNE employs a large language model (LLM) to identify implicit semantic constraints and generate affinity-based resource augmentation to resolve physical dependency issues. Second, it constructs a resource similarity-aware neural network, utilizing a pre-training and PPO fine-tuning strategy to precisely capture topological similarities between dynamic workflows and heterogeneous networks. By coupling semantic perception with topological reasoning, this mechanism effectively bridges the gap between dynamic service requirements and physical infrastructure. Simulation results demonstrate that AgentVNE reduces workflow communication latency to less than 40% of baselines and improves the service acceptance rate by approximately 5%-10% under high-load scenarios. Ultimately, this work provides a foundational solution for the semantic-aware deployment of agentic AI.
title AgentVNE: LLM-Augmented Graph Reinforcement Learning for Affinity-Aware Multi-Agent Placement in Edge Agentic AI
topic Networking and Internet Architecture
url https://arxiv.org/abs/2601.02021