MAS-H2: A Hierarchical Multi-Agent System for Holistic Cloud-Native Autoscaling

• URL: http://arxiv.org/abs/2603.07607v1
• Date: Sun, 08 Mar 2026 12:39:14 GMT
• Title: MAS-H2: A Hierarchical Multi-Agent System for Holistic Cloud-Native Autoscaling
• Abstract summary: We present MAS-H2, a new hierarchical multi-agent system that addresses the challenges of autonomic cloud resource management.<n>We built and tested a MAS-H2 prototype as a Operator on Google Engine (GKE) to benchmark it against the native Horizontal Pod Autoscaler (HPA) and Cluster Autoscaler (CA)<n>Results show that the MAS-H2 system maintained application CPU usage under 40% for predictable Heartbeat workloads.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoscaling in cloud-native platforms like Kubernetes is reactive and metric-driven, leading to a strategic void problem. This comes from the decoupling of higher-level business policies from lower-level resource provisioning. The strategic void, coupled with a fragmented coordination of pod and node scaling, can lead to significant resource waste and performance degradation under dynamic workloads. In this paper, we present MAS-H2, a new hierarchical multi-agent system that addresses the challenges of autonomic cloud resource management with a complete end-to-end solution. MAS-H2 systematically decomposes the control problem into three layers: a Strategic Agent that formalises business policies (e.g., cost vs. performance) into a global utility function; Planning Agents that produce a joint, proactive scaling plan for pods and nodes with time-series forecasting; and Execution Agents that execute the scaling plan. We built and tested a MAS-H2 prototype as a Kubernetes Operator on Google Kubernetes Engine (GKE) to benchmark it against the native Horizontal Pod Autoscaler (HPA) and Cluster Autoscaler (CA) baselines under two realistic, spiky, and stress-inducing workload scenarios. The results show that the MAS-H2 system maintained application CPU usage under 40% for predictable Heartbeat workloads. This resulted in over 50% less sustained CPU stress than the native HPA baseline, which typically operated above 80%. The MAS-H2 system demonstrated proactive planning in a volatile Chaotic Flash Sale scenario by filtering transient noise and deploying more replicas compared to HPA. It reduced peak CPU load by 55% without under-provisioning. Beyond performance, MAS-H2 seamlessly performed a zero-downtime strategic migration between two cost- and performance-optimised infrastructures.

Related papers

• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling [4.857151634248649]
  Large language models are increasingly deployed as complex agentic systems that scale with task complexity.<n>At the algorithm level, allocating additional inference-time can enhance workflow capacity but introduces cross-path redundancy.<n>At the task level, complex tasks can be decomposed into subproblems and delegated across multiple agents for improved scalability and parallelism.<n>We propose Hive, a multi-agent infrastructure that enables algorithm- and task-level scaling.
  arXiv  Detail & Related papers  (2026-04-19T09:59:35Z)
• Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems [51.2882705779387]
  Cloud-OpsBench is a large-scale benchmark that employs a State Snapshot Paradigm to construct a deterministic digital twin of the cloud.<n>It features 452 distinct fault cases across 40 root cause types spanning the full stack.
  arXiv  Detail & Related papers  (2026-02-28T05:04:42Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• Agentic Test-Time Scaling for WebAgents [65.5178428849495]
  We present Confidence-Aware Test-Time Scaling (CATTS), which uses vote-derived uncertainty to allocate compute only when decisions are genuinely contentious.<n>CATTS improves performance on WebArena-Lite and GoBrowse by up to 9.1% over React while using up to 2.3x fewer tokens than uniform scaling.
  arXiv  Detail & Related papers  (2026-02-12T18:58:30Z)
• LASER: An Efficient Target-Aware Segmented Attention Framework for End-to-End Long Sequence Modeling [20.507605423606282]
  We present LASER, a full-stack optimization framework developed and deployed at Xiaohongshu (RedNote)<n>System efficiency: We introduce SeqVault, a unified schema-aware serving infrastructure for long user histories.<n>Algorithmic efficiency: We propose a Segmented Target Attention (STA) mechanism to address the computational overhead.
  arXiv  Detail & Related papers  (2026-02-12T04:33:37Z)
• Astraea: A State-Aware Scheduling Engine for LLM-Powered Agents [12.884297990127985]
  Astraea is a service engine designed to shift the optimization from local segments to the global request lifecycle.<n>It employs a state-aware, hierarchical scheduling algorithm that integrates a request's historical state with future predictions.<n>Astraea reduces average JCT by up to 25.5% compared to baseline methods.
  arXiv  Detail & Related papers  (2025-12-16T06:55:10Z)
• UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action [77.63125913907771]
  We present UltraCUA, a foundation model that bridges the gap between GUI primitives and high-level programmatic tool calls.<n>Experiments with our 7B and 32B models demonstrate substantial improvements over state-of-the-art agents.
  arXiv  Detail & Related papers  (2025-10-20T17:48:26Z)
• Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol [0.7288110873705294]
  Anemoi is a semi-centralized MAS built on the Agent-to-Agent (A2A) communication MCP server from Coral Protocol.<n>Unlike traditional designs, Anemoi enables structured and direct inter-agent collaboration, allowing all agents to monitor progress, assess results, identify bottlenecks, and propose refinements in real time.
  arXiv  Detail & Related papers  (2025-08-23T15:45:10Z)
• Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC [11.82567747365518]
  This paper introduces Agent.xpu, an efficient serving system for agentic LLM workloads on memory-unified heterogeneous SOCs.<n>With dedicated offline profiling, Agent.xpu first constructs a heterogeneous execution graph, which fuses and chunks model kernels for affinity-guided, elastic accelerator mapping.<n>At runtime, its online scheduler enables fine-grained, kernel-level preemption to guarantee the responsiveness of reactive tasks.
  arXiv  Detail & Related papers  (2025-06-30T16:50:48Z)
• Streamlining Resilient Kubernetes Autoscaling with Multi-Agent Systems via an Automated Online Design Framework [0.0]
  Cloud-native systems often face challenges to their operational resilience due to poor workload management issues.<n>We propose decomposing the overarching goal of maintaining operational resilience into failure-specific sub-goals delegated to collaborative agents.<n>We introduce an automated, four-phase online framework for HPA MAS design: 1) modeling a digital twin built from cluster traces; 2) training agents in simulation using roles and missions tailored to failure contexts; 3) analyzing agent behaviors for explainability; and 4) transferring learned policies to the real cluster.
  arXiv  Detail & Related papers  (2025-05-26T20:39:31Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.