We investigate task-success-oriented resource allocation for federated split learning (FSL) at the wireless edge. In this setting, the server must jointly determine bandwidth, transmit power, split-layer placement, compression level, and terminal participation under per-round deadline, memory, and spectrum constraints. These coupled decisions affect wireless transmission, model training, and task execution, which evolve at different time scales and cannot be efficiently evaluated through repeated real-world trials. To address this challenge, we propose TiLP, a twin-in-the-loop planner that evaluates candidate decisions through a cross-domain digital twin before execution. The twin integrates network, training, and task sub-twins, with each sub-twin calibrated at the time scale of the process it models. Based on this twin, TiLP performs receding-horizon cross-entropy method planning with actor-critic guidance to search over mixed continuous-discrete decisions. Experiments on LIBERO robotic manipulation tasks over a Sionna RT-simulated wireless network show that TiLP improves task success by 9.5 percentage points over the strongest single-axis baseline, while satisfying the per-round deadline and energy budget.

翻译：本文研究无线边缘环境下面向任务成功率的联邦拆分学习（FSL）资源分配问题。在该场景中，服务器需在每轮截止时间、内存和频谱约束下，联合确定带宽、发射功率、拆分层配置、压缩等级及终端参与决策。这些耦合决策影响无线传输、模型训练与任务执行，三者具有不同时间尺度演化特征，无法通过反复真实实验高效评估。针对此挑战，我们提出TiLP——一种双生体闭环规划器，在执行前通过跨域数字孪生评估候选决策。该数字孪生集成网络孪生体、训练孪生体与任务孪生体，每个子孪生体以所建模过程的时间尺度进行校准。基于该孪生体，TiLP采用带有演员-评论家引导的滚动时域交叉熵方法规划，在连续-离散混合决策空间进行搜索。基于Sionna RT仿真无线网络的LIBERO机器人操作任务实验表明，TiLP在满足每轮截止时间与能量预算的前提下，相较于最强单轴基线，任务成功率提升9.5个百分点。