FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
On the map: LLM agents and tool use → Agentic AI for wireless networks
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use. Builds on 12 of its 15 references that are in the map. First posted on arXiv 20 Aug 2026.
Builds on
12 of 15 references.
Closest ancestors · 2
Same direction, newest first
- 2026ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks27 Jan
- 2025Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents16 Oct
Other references · 10
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,758
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,365
- 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
- 2019Fair Resource Allocation in Federated Learningcited by 390
- 2023Topology-aware Federated Learning in Edge Computing: A Comprehensive Surveycited by 23
- 2023FedLE: Federated Learning Client Selection with Lifespan Extension for Edge IoT Networkscited by 3
- 2025Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environmentcited by 3
- 2025Tool-Aided Evolutionary LLM for Generative Policy Toward Efficient Resource Management in Wireless Federated Learningcited by 2
- 2025Client Selection in Federated Learning with Data Heterogeneity and Network Latenciescited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Agentic Federated Learning: The Future of Distributed Training Orchestration
- 2024Federated In-Context LLM Agent Learning
- 2026Auto-FL-Research: Agentic Search for Federated Learning Algorithms
- 2026Agentic Federated Learning: Rule-Based Client and Server Agents for Adaptive Training
- 2026Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation
- 2024eFedLLM: Efficient LLM Inference Based on Federated Learning
- 2025Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents
- 2024FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts