AGMARL-DKS: An Adaptive Graph-Enhanced Multi-Agent Reinforcement Learning for Dynamic Kubernetes Scheduling

• URL: http://arxiv.org/abs/2603.12031v1
• Date: Thu, 12 Mar 2026 15:09:48 GMT
• Title: AGMARL-DKS: An Adaptive Graph-Enhanced Multi-Agent Reinforcement Learning for Dynamic Kubernetes Scheduling
• Abstract summary: Cloud-native applications require intelligent schedulers that can balance system stability, resource utilisation, and associated costs.<n>Current reinforcement learning-based schedulers have three major limitations.<n>We propose the Adaptive Graph-enhanced Neural Multi-Agent Reinforcement Learning Dynamic Scheduler (AGMARL-DKS)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art cloud-native applications require intelligent schedulers that can effectively balance system stability, resource utilisation, and associated costs. While Kubernetes provides feasibility-based placement by default, recent research efforts have explored the use of reinforcement learning (RL) for more intelligent scheduling decisions. However, current RL-based schedulers have three major limitations. First, most of these schedulers use monolithic centralised agents, which are non-scalable for large heterogeneous clusters. Second, the ones that use multi-objective reward functions assume simple, static, linear combinations of the objectives. Third, no previous work has produced a stress-aware scheduler that can react adaptively to dynamic conditions. To address these gaps in current research, we propose the Adaptive Graph-enhanced Multi-Agent Reinforcement Learning Dynamic Kubernetes Scheduler (AGMARL-DKS). AGMARL-DKS addresses these gaps by introducing three major innovations. First, we construct a scalable solution by treating the scheduling challenge as a cooperative multi-agent problem, where every cluster node operates as an agent, employing centralised training methods before decentralised execution. Second, to be context-aware and yet decentralised, we use a Graph Neural Network (GNN) to build a state representation of the global cluster context at each agent. This represents an improvement over methods that rely solely on local observations. Finally, to make trade-offs between these objectives, we use a stress-aware lexicographical ordering policy instead of a simple, static linear weighting of these objectives. The evaluations in Google Kubernetes Engine (GKE) reveal that AGMARL-DKS significantly outperforms the default scheduler in terms of fault tolerance, utilisation, and cost, especially in scheduling batch and mission-critical workloads.

Related papers

• Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems [28.41165257733149]
  Large language models (LLMs) enable autonomous agents for reasoning, planning, computation and tool use.<n>Recent systems increasingly organize these agents as graphs of specialized, interconnected nodes.<n>Existing approaches often execute graph components uniformly, wasting resources on irrelevant or low-impact tasks.<n>We introduce textbfAttention Orchestration, a paradigm that extends Transformer-style attention from token representations to workflow-level agent coordination.
  arXiv  Detail & Related papers  (2026-07-26T14:23:33Z)
• Beyond Quantity: Trajectory Diversity Scaling for Code Agents [51.71414642763219]
  Trajectory Diversity Scaling is a data synthesis framework for code agents that scales performance through diversity rather than raw volume.<n> TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; and (3) an adaptive evolution mechanism that steers toward long-tail scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:43:03Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Reinforcement Learning for Machine Learning Engineering Agents [52.03168614623642]
  We show that agents backed by weaker models that improve via reinforcement learning can outperform agents backed by much larger, but static models.<n>We propose duration- aware gradient updates in a distributed asynchronous RL framework to amplify high-cost but high-reward actions.<n>We also propose environment instrumentation to offer partial credit, distinguishing almost-correct programs from those that fail early.
  arXiv  Detail & Related papers  (2025-09-01T18:04:10Z)
• AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems [22.291969093748005]
  AgentNet is a decentralized, Retrieval-Augmented Generation (RAG)-based framework for multi-agent systems.<n>Unlike prior approaches with static roles or centralized control, AgentNet allows agents to adjust connectivity and route tasks based on local expertise and context.<n>Experiments show that AgentNet achieves higher task accuracy than both single-agent and centralized multi-agent baselines.
  arXiv  Detail & Related papers  (2025-04-01T09:45:25Z)
• 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)
• Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing [93.67044879636093]
  This paper addresses the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. We propose a graph reinforcement learning-based early-exit mechanism (GRLE) which outperforms the state-of-the-art work. The experimental results show that GRLE achieves the average accuracy up to 3.41x over graph reinforcement learning (GRL) and 1.45x over DROOE.
  arXiv  Detail & Related papers  (2022-10-24T07:17:20Z)
• Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning [114.36124979578896]
  We design a dynamic mechanism using offline reinforcement learning algorithms. Our algorithm is based on the pessimism principle and only requires a mild assumption on the coverage of the offline data set.
  arXiv  Detail & Related papers  (2022-05-05T05:44:26Z)
• Hybrid intelligence for dynamic job-shop scheduling with deep reinforcement learning and attention mechanism [28.28095225164155]
  We formulate the DJSP as a Markov decision process (MDP) to be tackled by reinforcement learning (RL) We propose a flexible hybrid framework that takes disjunctive graphs as states and a set of general dispatching rules as the action space with minimum prior domain knowledge. We present Gymjsp, a public benchmark based on the well-known OR-Library, to provide a standardized off-the-shelf facility for RL and DJSP research communities.
  arXiv  Detail & Related papers  (2022-01-03T09:38:13Z)
• Smart Scheduling based on Deep Reinforcement Learning for Cellular Networks [18.04856086228028]
  We propose a smart scheduling scheme based on deep reinforcement learning (DRL) We provide implementation-friend designs, i.e., a scalable neural network design for the agent and a virtual environment training framework. We show that the DRL-based smart scheduling outperforms the conventional scheduling method and can be adopted in practical systems.
  arXiv  Detail & Related papers  (2021-03-22T02:09:16Z)
• Dif-MAML: Decentralized Multi-Agent Meta-Learning [54.39661018886268]
  We propose a cooperative multi-agent meta-learning algorithm, referred to as MAML or Dif-MAML. We show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.
  arXiv  Detail & Related papers  (2020-10-06T16:51:09Z)
• Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments using A3C learning and Residual Recurrent Neural Networks [30.61220416710614]
  A-Advantage-Actor-Critic (A3C) learning is known to quickly adapt to dynamic scenarios with less data and Residual Recurrent Neural Network (R2N2) to quickly update model parameters. We use the R2N2 architecture to capture a large number of host and task parameters together with temporal patterns to provide efficient scheduling decisions. Experiments conducted on real-world data set show a significant improvement in terms of energy consumption, response time, ServiceLevelAgreement and running cost by 14.4%, 7.74%, 31.9%, and 4.64%, respectively.
  arXiv  Detail & Related papers  (2020-09-01T13:36:34Z)

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.