arXiv:2409. 15723v3 Announce Type: replace Abstract: Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy and governance concerns.
arXiv:2606. 10595v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning.
FedSkillGit is a federated framework that enables large language model agents to evolve reusable natural‑language skills without sharing raw data. Instead of uploading entire skill documents, clients submit bounded patches and local experience summaries, which are filtered for privacy, deduplicated, and merged into a global skill candidate. The server distributes the candidate for client‑side validation, publishing it only when performance improves, and experiments show it outperforms baselines by up to 22% while approaching centralized results.
The paper argues that distributed learning—federated and decentralized—should be a core approach for large language model post‑training, rather than an optional privacy measure. It critiques current methods like RLHF and DPO for assuming centralized preference data, citing scientific, practical, and ethical flaws. The authors present a three‑pillar framework (privacy and data sovereignty, pluralism and representational equity, robustness and scalability), formalize technical challenges such as reference drift and preference heterogeneity, and outline algorithmic directions and a research agenda to make distributed post‑training feasible.
arXiv:2606. 16891v1 Announce Type: cross Abstract: Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to capture the full scope of modern payloads like synthetic data and federated analytics.
arXiv:2608. 13844v1 Announce Type: cross Abstract: Large language models (LLMs) have become core components of cloud-based intelligent services in academia and industry, yet their training and deployment are hindered by high computational costs, data centralization, and privacy concerns.
The paper introduces SAPE-FL, a personalization framework for Federated Learning that anchors each client’s model to both a global model and a similarity-weighted peer-averaged model. By applying dynamic, client-specific regularization based on model and output similarity, SAPE-FL balances global knowledge transfer with peer collaboration, filtering out dissimilar clients. The authors provide theoretical convergence guarantees and demonstrate empirically that SAPE-FL outperforms state‑of‑the‑art methods in highly heterogeneous and low‑data scenarios.
arXiv:2606. 03143v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement.
arXiv:2602.04093v3 Announce Type: replace Abstract: Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept an...
arXiv:2505. 19699v2 Announce Type: replace-cross Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy.
The paper introduces a federated active learning (FAL) approach that tackles data privacy and label scarcity by coordinating query selection across clients. In low-budget scenarios, it finds that homogeneous (IID) data actually requires stronger coordination to avoid redundant queries, while heterogeneous data naturally yields diversity—a reversal of the usual federated learning narrative. The authors propose a new framework that aligns client data in a shared embedding space via federated representation learning, enabling globally coordinated active selection while keeping annotations local, and demonstrate that this method outperforms existing FAL methods even with larger annotation budgets.
arXiv:2608. 02250v1 Announce Type: new Abstract: Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally updated models.