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

Researchers introduce Auto-FL-Research (AFR), a constrained coding-agent workflow designed to automate the search and optimization of Federated Learning algorithms. This approach addresses the costly manual trial-and-error process, paving the way for more efficient decentralized AI development.

Computer Science > Artificial Intelligence

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

View PDF HTML (experimental)Abstract: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.

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations

Researchers have introduced PACE, a novel neuro-symbolic framework designed to generate plausible and actionable counterfactual explanations for machine learning models. By separating neural prediction from symbolic reasoning, PACE successfully addresses the limitations of traditional methods that often produce unrealistic recommendations.

agentic-systems

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

A new research introduces Procedural Memory Distillation (PMD), allowing large language models to learn from past rollouts to self-improve. PMD significantly boosts model performance on coding and scientific benchmarks without adding computational overhead during inference.

agentic-systems

CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse

Researchers introduce CreativityNeuro, a data-free method that enhances divergent thinking in LLMs via contrastive weight steering, significantly reducing mode collapse and improving creative performance without re-training.

agentic-systems

The Wiola Architecture for Efficient Small Language Models

Researchers have introduced Wiola, a novel Small Language Model (SLM) architecture built from first principles without inheriting from GPT or LLaMA. Featuring five core technological innovations, Wiola promises superior performance and optimized computational efficiency for small-scale AI models.

agentic-systems

Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection

Researchers have proposed a new constrained, verifiable agent framework that shifts LLM output from free-form code to typed JSON configurations, addressing common web scraping errors. This approach minimizes operational costs by using zero LLM tokens during execution while ensuring high reusability.

agentic-systems

Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows

Researchers introduce Mnemosyne, an open-source runtime utilizing Agentic Transaction Processing (ATP) to validate and repair AI-generated workflows, ensuring system correctness and safety against untrusted proposals from Large Language Models (LLMs).

EXPLORE TOPICS