mlsanityData to 14 Oct 2026

Auto-FL-Research: Agentic Search for Federated Learning Algorithms

arXiv 2607.01366 ↗First posted 1 Jul 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agentic AI for wireless networks

Abstract (arXiv)

Federated learning (FL) research often depends on many small but consequential algorithmic choices: optimizer variants, server aggregation rules, local training schedules, normalization, regularization, and model architecture. These choices are expensive to explore manually and difficult to compare fairly when candidate changes can also alter the FL training or evaluation path. In this work, we present Auto-FL-Research (AFR), a constrained coding-agent workflow for FL algorithmic recipe search. Agents may propose and implement candidate training algorithms, including server aggregation rules, client update schedules, local objectives, and registered model variants, while task profiles fix the mutation surface, compute budget, communication contract, and final model evaluation. Each campaign records candidate scores, runtime, edited files, artifacts, and failure status. We evaluate AFR on five healthcare cross-silo FLamby tasks and on grouped-client profiles for the five fixed LEAF datasets plus the LEAF synthetic task. Five-seed repeat evaluations support gains on four FLamby tasks and five of six LEAF profiles, while also exposing seed-sensitive and search-selected failure cases. Same-budget controls show that several gains correspond to FL-recipe changes, whereas other improvements are recovered by fixed-surface scalar controls or fail under repeat or held-out evaluation. These mixed outcomes are part of the contribution: they show how agent-generated candidates can be separated into repeated FL mechanisms, fixed-surface tuning effects, and selected single-run artifacts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use. Builds on 23 of its 30 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

23 of 30 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  5. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  6. 2020Adaptive Federated Optimizationcited by 1,046
  7. 2018LEAF: A Benchmark for Federated Settingscited by 792
  8. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  9. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  10. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
  11. 2019AutoML: A Survey of the State-of-the-Artcited by 390
  12. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
11 more
  1. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 80
  2. 2020From Federated Learning to Federated Neural Architecture Search: A Surveycited by 42
  3. 2021AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learningcited by 39
  4. 2021Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentationcited by 19
  5. 2022Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentationcited by 16
  6. 2023FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Schedulercited by 13
  7. 2024Revisiting Ensembling in One-Shot Federated Learningcited by 13
  8. 2025EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistantscited by 5
  9. 2026Camyla: Scaling Autonomous Research in Medical Image Segmentationcited by 5
  10. 2023Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergencecited by 3
  11. 2024Hyper-parameter Optimization for Federated Learning with Step-wise Adaptive Mechanismcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic Federated Learning: Rule-Based Client and Server Agents for Adaptive Training
  2. 2026Agentic Federated Learning: The Future of Distributed Training Orchestration
  3. 2025FedAgentBench: Towards Automating Real-world Federated Medical Image Analysis with Server-Client LLM Agents
  4. 2026FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
  5. 2025Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents
  6. 2026FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling
  7. 2025FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data
  8. 2026Agentic AI as a Network Control-Plane Intelligence Layer for Federated Learning over 6G