cs.MASep 21, 2026

IMPACT: Intent-driven Multi-agent Policy with Attention for SLO-guaranteed Microservice Migration in Cloud-edge Systems

Authors: Xinjin Li, Siru Tao, Shihan Yin, Yujian Long, Qingze Wang, Lu Cheng, Yeyang Zhou, Calvin Chang Liu, 

Organizations: Columbia University · Carnegie Mellon University · Brandeis University · Georgetown University · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Ensuring strict tail-latency service-level objectives (SLOs) in dynamic mobile edge computing (MEC) systems remains challenging because user mobility, wireless fading, bursty workloads, and partial observability jointly undermine reliable cloud-edge orchestration. Existing microservice migration methods predominantly optimize average delay and often decouple migration from bandwidth control, leading to uncoordinated decisions, queue oscillation, and frequent high-percentile latency violations. To address this issue, we propose IMPACT, an intent-driven Agentic AI framework for cooperative microservice migration and bandwidth control in cloud-edge systems. Under centralized training with decentralized execution (CTDE), each edge cloud is modeled as an autonomous agent that encodes local SLO risk, migration urgency, and computational pressure into compact, semantic intent representations. IMPACT further introduces a double-attention mechanism that first selectively aggregates relevant peer intents for efficient inter-agent communication and then filters local observations to emphasize goal-relevant state information. This design enables robust coordination under partial observability and jointly optimizes service migration and discrete uplink bandwidth allocation. Extensive experiments in 5-edge and 20-edge scenarios show that IMPACT reduces mean latency by 30-50% and tail-latency deviation by 40-70% compared with state-of-the-art factorized multi-agent reinforcement learning (MARL) and heuristic baselines, while achieving near-zero SLO violation rates under tight thresholds and energy consumption close to the best heuristic baseline. These results demonstrate that intent-driven agentic coordination provides an effective and scalable solution for SLO-aware orchestration in complex cloud-edge intelligent systems.

Figures & tables

Fig. 1: Dynamic edge environment and tail-latency challenge. (A) Dynamic edge conditions with migration and bandwidth control under partial observability. (B) Uncoordinated local actions can cause load imbalance, queue explosion, and oscillation. (C) These effects increase tail latency and SLO risk at high percentiles.
Fig. 2: Overview of IMPACT. A recurrent encoder produces a latent intent from local observations and previous actions. The double-attention core then performs inter-agent message attention and intra-agent environment attention before the policy outputs coordinated bandwidth and migration actions.
Fig. 3: CTDE training and decentralized execution in IMPACT. During training, a centralized global critic provides learning signals using the global state. During execution, each agent acts with local observations, its latent intent, and selectively shared intents, while reward shaping closes the loop with the dynamic environment.
Fig. 4: Test return in 20 edges scenario.
Fig. 5: The CDF of service migration average latency in the 20-edge.
Fig. 6: Ablation Result. “e” means the loss of environment attention, “m” means the loss of message attention, and “b” means both losses.
MethodCost ↓\downarrowLatency (ms) ↓\downarrowDeviation (%) ↓\downarrow
Random3.80423.600.217
Greedy3.40133.300.088
QMIX3.69187.500.091
QPLEX3.68186.500.088
VDN3.67174.700.083
MAIC3.66180.900.087
TABLE I: Performance comparison on 20 edges. Best results are in bold. Improvements are relative to the best baseline (excluding IDDA).
More in this topic

Edge-Cloud Computing

Edge-cloud computing distributes data processing and AI workloads between nearby devices and remote cloud services to balance latency, cost, energy, and scale.

See all 67 papers

Explore similar work

CardsList
Apr 8, 2026

Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing

Emerging computation-intensive applications impose stringent latency requirements on resource-constrained mobile devices. Mobile Edge Computing (MEC) addresses this challenge through task offloading. However, designing effective policies remains difficult due to dynamic task arrivals, time-varying channels, and the spatio-temporal coupling of server queues. Conventional heuristics lack adaptability, while Deep Reinforcement Learning (DRL) suffers from limited generalization and architectural rigidity, requiring retraining when network topology changes. Although Large Language Models (LLMs) offer semantic reasoning capabilities, standard Supervised Fine-Tuning (SFT) yields myopic policies that greedily minimize immediate latency without accounting for long-term system evolution. To address these limitations, we propose COMLLM, a generative framework that enables foresighted decision-making in MEC systems. COMLLM integrates Group Relative Policy Optimization (GRPO) with a Look-Ahead Collaborative Simulation (LACS) mechanism, which performs multi-step Monte Carlo rollouts while jointly modeling server queue dynamics. By incorporating these rollouts into the reward design, the framework captures the long-term impact of current decisions on future system states. Experimental results demonstrate that COMLLM achieves near-optimal latency and improved load-balancing fairness. Notably, it exhibits zero-shot topological scalability, allowing a model trained on small-scale networks to generalize to larger, unseen topologies without retraining, outperforming SFT, DRL, and heuristic baselines.

Ning Yang, Chuangxin Cheng, Haijun Zhang

Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China · School of Mechano-Electronic Engineering, Xidian University, Xi’an, 710071, China · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China

Edge ComputingLLM ReasoningRL for LLM Agents
AskPDF
Mar 3, 2026

Hybrid Orchestration of Edge AI and Microservices via Graph-based Self-Imitation Learning

Modern edge AI applications increasingly rely on microservice architectures that integrate both AI services and conventional microservices into complex request chains with stringent latency requirements. Effectively orchestrating these heterogeneous services is crucial for ensuring low-latency performance, yet remains challenging due to their diverse resource demands and strong operational interdependencies under resource-constrained edge environments. In particular, frequent interactions between services tightly couple deployment and routing decisions, yet existing approaches optimize them in isolation, leading to fundamentally inadequate system performance.In this paper, we propose SIL-GPO, a reinforcement learning framework that optimizes hybrid orchestration for edge AI microservice systems. SIL-GPO formulates the orchestration problem as a sequential decision-making task and leverages graph attention networks to encode service topologies and routing dependencies within the agent state representation. Moreover, SIL-GPO integrates a self-imitation learning strategy into proximal policy optimization, enabling the agent to prioritize and reuse high-reward trajectories. This guides policy updates towards globally promising solutions that standard RL often fails to discover under sparse rewards and large combinatorial action spaces. We conduct extensive experiments on trace-driven edge AI workloads, demonstrating that SIL-GPO significantly reduces end-to-end service latency and enhances resource utilization compared to state-of-the-art heuristic, metaheuristic, and deep RL baselines. Our framework offers a unified and scalable solution for efficient orchestration of AI services and microservices in the edge, paving the way for low-latency, high-performance edge AI deployments.

Chen Yang, Jin Zheng, Yang Zhuolin +4

School of Computer Science, South-Central Minzu University, Wuhan, China, 430074, and Key Laboratory of Cyber-Physical Fusion Intelligent Computing, State Ethnic Affairs Commission · Hubei Key Laboratory of Smart Internet Technology, School of Electronic Information and Communication, Huazhong University of Science and Technology, Wuhan, China, 430074 · Centre for Frontier AI Research, Agency for Science, Technology and Research (A*STAR), Singapore

Edge Computing
AskPDF
Aug 5, 2026

Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application

Time-sensitive networking (TSN) is increasingly integrated into mobile edge computing (MEC) to support applications with stringent latency requirements, such as extended reality (XR). However, existing TSN scheduling solutions predominantly rely on static optimization techniques or centralized learning models that are based on fixed traffic patterns, limiting their effectiveness in dynamic environments. In practice, MEC environments often host multiple co-located XR traffic flows whose characteristics evolve over time, creating complex inter-queue dependencies that current schedulers fail to capture. Addressing these challenges requires adaptive, decentralized scheduling mechanisms capable of coordinating multiple TSN queues under varying traffic conditions. To this end, this paper proposes a multi-agent reinforcement learning (MARL) framework for TSN scheduling, where each TSN queue is modeled as an autonomous agent. The Heterogeneous-Agent Proximal Policy Optimization (HAPPO) algorithm is employed to explicitly model inter-agent dependencies and jointly optimize service delivery across queues. The simulation results demonstrate that the proposed approach reduces average frame waiting times by up to 26.8% and worst-case delays by approximately 16.8%, highlighting its effectiveness in dynamic XR-driven MEC scenarios.

Marcos Carvalho, Fatih Temiz, Shavbo Salehi +2

Universidade Federal de Minas Gerais, Brazil · School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada

Multi-Agent CoordinationEdge ComputingMulti-Agent Reinforcement Learning
AskPDF