PubSwap: Public-Data Off-Policy Coordination for Federated RLVR

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nayak, Anupam, Askin, Baris, Ustaomeroglu, Muhammed, Joe-Wong, Carlee, Joshi, Gauri
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911591598915584
author Nayak, Anupam
Askin, Baris
Ustaomeroglu, Muhammed
Joe-Wong, Carlee
Joshi, Gauri
author_facet Nayak, Anupam
Askin, Baris
Ustaomeroglu, Muhammed
Joe-Wong, Carlee
Joshi, Gauri
contents Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentralized private data distributed across organizations. Federated training is a natural solution, but scaling RLVR in this regime is challenging: full-model synchronization is expensive, and performing many local steps can cause severe client drift under heterogeneous data. We propose a federated RLVR framework that combines LoRA-based local adaptation with public-data-based off-policy steps to improve both communication efficiency and cross-client coordination. In particular, a small shared public dataset is used to periodically exchange and reuse response-level training signals across organizations, providing a lightweight anchor toward a more globally aligned objective without exposing private data. Our method selectively replaces locally incorrect responses with globally correct ones during public-data steps, thereby keeping training closer to the local policy while still benefiting from cross-client coordination. Across mathematical and medical reasoning benchmarks and models, our method consistently improves over standard baselines. Our results highlight a simple and effective recipe for federated reasoning post-training: combining low-rank communication with limited public-data coordination.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12160
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
Nayak, Anupam
Askin, Baris
Ustaomeroglu, Muhammed
Joe-Wong, Carlee
Joshi, Gauri
Machine Learning
Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentralized private data distributed across organizations. Federated training is a natural solution, but scaling RLVR in this regime is challenging: full-model synchronization is expensive, and performing many local steps can cause severe client drift under heterogeneous data. We propose a federated RLVR framework that combines LoRA-based local adaptation with public-data-based off-policy steps to improve both communication efficiency and cross-client coordination. In particular, a small shared public dataset is used to periodically exchange and reuse response-level training signals across organizations, providing a lightweight anchor toward a more globally aligned objective without exposing private data. Our method selectively replaces locally incorrect responses with globally correct ones during public-data steps, thereby keeping training closer to the local policy while still benefiting from cross-client coordination. Across mathematical and medical reasoning benchmarks and models, our method consistently improves over standard baselines. Our results highlight a simple and effective recipe for federated reasoning post-training: combining low-rank communication with limited public-data coordination.
title PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
topic Machine Learning
url https://arxiv.org/abs/2604.12160