{"ID":2831325,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.08870","arxiv_id":"2512.08870","title":"Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents","abstract":"LLM 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, self-evolving 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 paradigm. Locally, agents employ parameter-efficient fine-tuning on filtered, high-return trajectories to achieve stable gradient updates. Globally, Fed-SE aggregates updates within a low-rank subspace, reducing communication cost across clients. Experiments across five heterogeneous environments demonstrate that Fed-SE improves average task success rates by 10\\% over the state-of-the-art FedIT, validating its effectiveness in cross-environment knowledge transfer under privacy constraints.","short_abstract":"LLM 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, self-evolving agent systems remains...","url_abs":"https://arxiv.org/abs/2512.08870","url_pdf":"https://arxiv.org/pdf/2512.08870v2","authors":"[\"Xiang Chen\",\"Yuling Shi\",\"Qizhen Lan\",\"Yuchao Qiu\",\"Min Wang\",\"Xiaodong Gu\",\"Yanfu Yan\"]","published":"2025-12-09T18:04:41Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}