Federated reasoning LLMs: a survey

Shuyue Wei, Yongxin Tong, Zimu Zhou, Yi Xu, Jingkai Gao, Tongyu Wei, Tianran He, Weifeng Lv

Abstract: Reasoning has long been regarded as a distinctive hallmark of human cognition, and recent advances in the artificial intelligence community have increasingly focused on the reasoning large language models (rLLMs). However, due to strict privacy regulations, the domain-specific reasoning knowledge is often distributed across multiple data owners, limiting the rLLM’s ability to fully leverage such valuable resources. In this context, federated learning (FL) has gained increasing attention in both the academia and industry as a promising privacy-preserving paradigm for addressing the challenges in the data-efficient training of rLLMs.