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

TL;DR

AgentVNE introduces an LLM-augmented graph reinforcement learning framework that enhances multi-agent placement in edge computing, addressing dynamic workflows and affinity constraints for improved latency and acceptance rates.

Contribution

It presents a novel dual-layer framework combining semantic constraint identification with topological similarity learning for dynamic multi-agent deployment.

Findings

Reduces workflow communication latency to less than 40% of baselines.

Increases service acceptance rate by 5%-10% under high load.

Effectively bridges semantic and topological gaps in edge resource allocation.

Abstract

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.