Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents

February 09, 2026

Reading time: 2 minute

...

📝 Original Info

Title: Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents
ArXiv ID: 2512.08870
Date: 2025-12-09
Authors: Xiang Chen, Yuling Shi, Qizhen Lan, Yuchao Qiu, Min Wang, Xiaodong Gu, Yanfu Yan

📝 Abstract

LLM (Large Language Model) agents are widely deployed in complex interactive tasks, yet privacy constraints often preclude centralized optimization and co-evolution across dynamic environments. Despite the demonstrated success of Federated Learning (FL) on static datasets, its effectiveness in open-ended, selfevolving agent systems remains largely unexplored. In such settings, the direct application of standard FL is particularly challenging, as heterogeneous tasks and sparse, trajectory-level reward signals give rise to severe gradient instability, which undermines the global optimization process. To bridge this gap, we propose Fed-SE, a Federated Self-Evolution framework for LLM agents that establishes a local evolution-global aggregation...

📄 Full Content

LLM-based agents have demonstrated significant potential in complex interactive tasks, ranging from embodied intelligence to online service systems (Zitkovich et al., 2023;Belkhale et al., 2024;Li et al., 2025b;Peng et al., 2025;Shi et al., 2024;OpenAI et al., 2024;Shi et al., 2025a;Yang et al., 2025b;Zhang et al., 2025c,d,e). The enhancement of agent capabilities typically relies on the accumulation of experience through continuous interaction with environments (Liu et al., 2025;Chen et al., 2025;Fang et al., 2025;Cai et al., 2025), which enables agents to internalize ta

…(Content truncated for length.)

📄 Read Full PDF on ArXiv