FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning

• URL: http://arxiv.org/abs/2608.20518v1
• Date: Thu, 20 Aug 2026 19:27:52 GMT
• Title: FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
• Abstract summary: In Federated Learning (FL), the communication topology is a runtime variable rather than a fixed design choice.<n>We propose FL-MAESTRO, a multi-agent orchestrator that makes the joint runtime FL decision directly through three specialist LLM agents.<n>A coordinator combines their analyses into a single decision, and a non-LLM feasibility check confirms it before the round executes.
• Score: 48.01654166701974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In Federated Learning (FL), the communication topology is a runtime variable rather than a fixed design choice, since links and edge devices drop in and out during training. Each round, the server must commit three coupled decisions, namely the communication topology, per-client resource allocation, and the aggregation rule for combining local updates. Recent agentic systems have begun bringing large language models (LLM) into FL, but the existing line of work either operates at setup time or handles a single runtime dimension such as client selection. We propose FL-MAESTRO, a multi-agent orchestrator that makes the joint runtime FL decision directly through three specialist LLM agents, one per decision dimension. A coordinator combines their analyses into a single decision, and a non-LLM feasibility check confirms it before the round executes. Because the orchestrator consumes the server's predicted-failure list, it withholds clients whose updates would never be aggregated, which removes the dominant source of wasted round energy in classical FL on volatile edge networks. Because client state is read as natural-text profiles, the same orchestrator extends to heterogeneous device classes without per-class energy models. On a non-IID CIFAR-10 benchmark, FL-MAESTRO matches the accuracy of the strongest energy-aware baseline while cutting wasted round energy from over a third to near zero. Code is available at https://github.com/denoslab/FL-MAESTRO.

Related papers

• UnifyFL: Enabling Decentralized Cross-Silo Federated Learning [0.0]
  We develop a trust-based cross-silo Federated Learning framework called UnifyFL.<n>Our evaluation on a diverse testbed shows that UnifyFL achieves a performance comparable to the ideal multilevel centralized FL.
  arXiv  Detail & Related papers  (2025-04-26T13:15:40Z)
• SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead [75.87007729801304]
  SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead.<n>To optimize the pruning process itself, only thresholds are communicated between a server and clients instead of parameters.<n>Global thresholds are used to update model parameters by extracting aggregated parameter importance.
  arXiv  Detail & Related papers  (2024-06-01T13:10:35Z)
• Communication Efficient ConFederated Learning: An Event-Triggered SAGA Approach [67.27031215756121]
  Federated learning (FL) is a machine learning paradigm that targets model training without gathering the local data over various data sources. Standard FL, which employs a single server, can only support a limited number of users, leading to degraded learning capability. In this work, we consider a multi-server FL framework, referred to as emphConfederated Learning (CFL) in order to accommodate a larger number of users.
  arXiv  Detail & Related papers  (2024-02-28T03:27:10Z)
• Venn: Resource Management for Collaborative Learning Jobs [24.596584073531886]
  Collaborative learning (CL) has emerged as a promising approach for machine learning (ML) and data science across distributed edge devices.<n>In this paper, we present Venn, a CL resource manager that efficiently schedules heterogeneous devices among multiple CL jobs.<n>Our evaluation shows that, compared to the state-of-the-art CL resource managers, Venn improves the average JCT by up to 1.88x.
  arXiv  Detail & Related papers  (2023-12-13T17:13:08Z)
• Joint Age-based Client Selection and Resource Allocation for Communication-Efficient Federated Learning over NOMA Networks [8.030674576024952]
  In federated learning (FL), distributed clients can collaboratively train a shared global model while retaining their own training data locally. In this paper, a joint optimization problem of client selection and resource allocation is formulated, aiming to minimize the total time consumption of each round in FL over a non-orthogonal multiple access (NOMA) enabled wireless network. In addition, a server-side artificial neural network (ANN) is proposed to predict the FL models of clients who are not selected at each round to further improve FL performance.
  arXiv  Detail & Related papers  (2023-04-18T13:58:16Z)
• Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach [20.300740276237523]
  Federated learning (FL) is an emerging machine learning (ML) paradigm used to train models across multiple nodes (i.e., clients) holding local data sets. We develop a novel algorithm to achieve this goal, dubbed Bandit Scheduling for FL (BSFL)
  arXiv  Detail & Related papers  (2023-03-18T09:45:58Z)
• Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework [82.36466358313025]
  We propose a primal-dual FL algorithm, termed FedVRA, that allows one to adaptively control the variance-reduction level and biasness of the global model. Experiments based on (semi-supervised) image classification tasks demonstrate superiority of FedVRA over the existing schemes.
  arXiv  Detail & Related papers  (2022-12-03T03:27:51Z)
• Confederated Learning: Federated Learning with Decentralized Edge Servers [42.766372620288585]
  Federated learning (FL) is an emerging machine learning paradigm that allows to accomplish model training without aggregating data at a central server. We propose a ConFederated Learning (CFL) framework, in which each server is connected with an individual set of devices. The proposed algorithm employs a random scheduling policy which randomly selects a subset of devices to access their respective servers at each iteration.
  arXiv  Detail & Related papers  (2022-05-30T07:56:58Z)
• STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning [58.6792963686231]
  Federated Learning (FL) refers to the paradigm where multiple worker nodes (WNs) build a joint model by using local data. It is not clear how to choose the WNs' minimum update directions, the first minibatch sizes, and the local update frequency. We show that there is a trade-off curve between local update frequencies and local mini sizes, on which the above complexities can be maintained.
  arXiv  Detail & Related papers  (2021-06-19T06:13:45Z)
• Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation [119.19061102064497]
  We propose a decentralized FL framework by integrating blockchain into FL, namely, blockchain assisted decentralized federated learning (BLADE-FL) In a round of the proposed BLADE-FL, each client broadcasts its trained model to other clients, competes to generate a block based on the received models, and then aggregates the models from the generated block before its local training of the next round. We explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
  arXiv  Detail & Related papers  (2021-01-18T07:19:08Z)

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.